2025-05-08
美國參議會聽證會證詞 

2025-05-08  美國參議會聽證會，討論如何透過加強美國在計算和創新方面的能力來贏得人工智慧競賽 ，四位證人證詞與回答摘要 ( by Gemini 2.5 Pro )
OpenAI 聯合創始人兼執行長 Sam Altman
AMD 執行長兼董事長蘇姿豐 (Lisa Su)
CoreWeave 聯合創始人兼執行長 Michael Intrator
微軟公司副董事長兼總裁 Brad Smith。

Prompt: "這是一場參議院聽證會轉播的逐字稿，請節錄出四位證人 ( Sam Altman ， Lisa 蘇姿丰，Michael Intrator，Brad Smith ) 的證詞跟回答質問的重點，並以台灣的繁體中文轉述。 "

聽證會核心議題： 美國如何在AI競賽中保持領先，特別是相對於中國；政府應扮演何種角色（輕度監管vs. 強力介入）；以及AI發展所需的基礎設施、人才和國際合作。

1. Sam Altman (OpenAI 共同創辦人兼執行長)

• 開場證詞重點：

  • ChatGPT 現已成為全球第五大網站，每週超過5億人使用，顯著提升生產力、輔助醫療與學習。

  • 強調美國在AI領域的領導地位至關重要，AI的變革性可能超越網際網路。

  • 未來十年將是「充裕智能」與「充裕能源」的時代，美國需在這兩方面領先。

  • 以個人在網際網路時代成長的經歷為例，強調美國的創新精神與創業環境是AI革命發生在此地的關鍵，呼籲政策應延續這種精神。

  • 提及在德州Abalene建造全球最大的AI訓練設施（Stargate計畫）。

• 問答環節重點：

  • 政府角色： 應簡化大型建設計畫的流程，制定有利於加速創新的政策。

  • 贏得AI競賽：

    • 基礎設施： 確保基礎設施（資料中心、電力、國內晶片/伺服器生產）建設的確定性。

    • 全球合作： 吸引全球投資美國，允許盟友使用美國技術。

    • 人才： 吸引全球頂尖人才。

    • 法規： 需要清晰、輕觸式的監管框架，類似網際網路早期模式，避免過早或過嚴的標準扼殺創新。反對各州拼湊式的監管。

  • NIST標準： 有幫助，但非絕對必要，產業應主導標準制定。

  • 兒童安全： 承認網際網路在保護兒童方面做得不夠好，AI應對兒童有更高保護，對成人可更寬鬆。

  • 美中AI現況： 美國模型（如OpenAI、Google）目前領先，但差距不大。

  • 歐盟式監管： 若美國採納將是災難性的，會損害美國在運算、演算法、數據三大關鍵要素上的競爭力。

  • 開源模型： OpenAI計劃夏季發布一個領先的開源模型，鼓勵基於美國技術棧開發。

  • 能源： 對AI未來極其重要，AI成本最終將趨近於能源成本。

  • DeepSeek（中國AI模型）： 模型本身非重大事件，好的開源模型會有很多。其消費者應用程式曾短暫超越ChatGPT下載量，但美國應用程式仍佔主導。

  • AI擴散規則（已撤銷）： 樂見其撤銷。應有「贏得擴散」而非「阻止擴散」的思維，但核心研發（如模型訓練）應留在美國。

2. Lisa Su 蘇姿丰博士 (AMD 董事長兼執行長)

• 開場證詞重點：

  • AMD提供高效能晶片，支持關鍵任務如國防、科研，並與能源部合作打造全球最快的兩台超級電腦。

  • AI是時代最具變革性的技術，美國目前領先，但領導地位並非理所當然，這是一場全球競賽。

  • 維持領先的五大關鍵：

    1. 持續加速： 確保運算資源可用性。

    2. 開放生態系： 美國領導力的基石。

    3. 強健的國內供應鏈： 更多美國製造，公私協力。

    4. 投資人才： 使美國成為AI研究與工作的最佳地點。

    5. 出口管制： 理解國安重要性，但美國技術的廣泛採用亦關鍵，若美國技術難以取得，他國技術將趁虛而入。

• 問答環節重點：

  • 政府角色： 制定政策協助在創新競賽中跑得更快。

  • 贏得AI競賽： 更多運算能力在美國由美國公司建造，美國技術廣泛被全球正確使用，簡明易執行的出口管制，製造回流，厚植人才。

  • NIST標準： 支持。

  • 出口策略： 讓盟友在適當管制下取得美國先進技術，各國也樂於採用美國技術。

  • 晶圓廠能耗： 半導體製造廠是高耗能產業，需要更多電力。

  • 美中晶片現況： 美國目前領先，但中國正在追趕，即使沒有最好的晶片也能完成很多事。

  • 人才： 美國擁有頂尖工程師，但仍需更多硬體、軟體、應用開發人才，支持高技術移民。

  • 硬體開放標準： 極具優勢，能促進多方創新，確保最佳解決方案，並有助於安全（不依賴單一生態系）。AMD支持開放模型。

3. Michael Intrator (CoreWeave 共同創辦人兼執行長)

• 開場證詞重點：

  • CoreWeave是AI超大規模運算服務商，營運30多個資料中心，管理25萬個GPU。

  • 現代AI需要超越傳統雲端的專用基礎設施（電力、冷卻、晶片、網路、儲存）。

  • 在基礎設施領域領先的國家將主導全球議程；中國是主要競爭對手。

  • 四大政策要素：

    1. 戰略投資穩定性： 可預測的政策框架，安全的供應鏈，鼓勵創新的監管環境。

    2. 能源基礎設施發展： 充裕且可負擔的能源，加速審批與監管改革。

    3. 全球市場准入： 平衡國安風險與美國AI技術的全球擴散。

    4. 公私協力與勞動力發展。

• 問答環節重點：

  • 政府角色： 允許供應鏈在合理的政策下發展。

  • NIST標準： 支持，共同詞彙能加速發展。

  • 雲端資源出口： 全球對AI有需求，若美國不介入，其他技術（即使次佳）也會填補空缺。

  • 美中基礎設施現況： 美國領先，但弱點在於大型解決方案的建置能力（審批、電力）。

  • 各州拼湊式監管： 造成摩擦，阻礙建設與擴展。巨額投資可能因特定地區不利法規而受困。審批過程「極其折磨人」。

  • 能源取得： 贏得競賽的關鍵之一，取得「大規模」電力是一大挑戰。現有基礎設施彈性將耗盡。

4. Brad Smith (微軟副董事長兼總裁)

• 開場證詞重點：

  • AI技術棧（基礎設施、平台、應用）環環相扣，成功彼此依賴。

  • 國會需提供的三方面支持：

    1. 創新： 更多基礎設施、更快的審批、更多電機技師、大學與聯邦研究機構的支持。

    2. 加速採用（AI擴散）： 技能培訓、教育。

    3. 出口： 美國僅佔全球4.5%人口，需與世界連結，適當的出口管制，贏得全球信任。

  • AI的目標是打造輔助人類變得更好、追求更好工作的工具，而非取代人類。

  • 永遠不要低估科技的力量，也永遠不要低估人類在獲得更好工具與技能後的潛力。

• 問答環節重點：

  • 政府角色： 更多電機技師，更廣泛的AI教育。

  • NIST標準： 支持。NIST採納標準，但產業應參與創建。美國需推動全球採納這些標準。

  • 新聞媒體/內容協商： 支持新聞業發展，支持媒體集體協商。版權問題需平衡創作者報酬與AI數據取用。

  • 美中AI現況： 美國在激烈競賽中領先。勝負關鍵在於誰的技術能被全球其他78%人口廣泛採用（參考華為/5G教訓）。需正確的出口管制，贏得全球信任，並建立惠及發展中國家的金融架構。

  • 歐盟式監管： 應避免預先批准制度，尤其是在州層級。

  • 標記AI生成內容： 整體上支持，特別是圖像、影音。C2PA是相關標準。

  • AI應用於政府服務： 未來可望實現用AI輕鬆處理駕照更新、路坑提報、保險理賠等（阿布達比已實現部分）。

  • 聯邦濕地許可： 美國項目審批的最大挑戰（陸軍工兵署負責），耗時18-24個月。

  • 出口管制（AI擴散規則）： 應取消對二線國家的數量上限，確保晶片不被轉移至中國或被不當使用者獲取。

  • 資料中心能耗與電費： 微軟承諾投入與其用電量相等的新電力至電網，並管理以確保其活動不提高社區電價（例如，微軟主動提議提高自身電費以支付電網升級費用）。

  • DeepSeek： 微軟不允許員工使用其App（數據回傳中國、宣傳疑慮）。其開源「模型」則經分析修改以移除有害部分。安全優先。

  • AI擴散規則（替代方案）： 簡化，取消二線國家數量限制。允許最先進GPU出口至由可信賴供應商運營、符合安全標準（物理、網路、防轉移、防有害用途如解放軍使用、生化武器開發等）的資料中心。

總結：
四位證人都強調美國在AI領域的領先地位及持續創新的重要性。他們普遍支持「輕觸式」的聯邦監管框架，反對歐盟式的嚴格預先審批或各州零散立法，認為這會扼殺創新並輸給中國。能源供應、基礎設施建設（特別是簡化審批流程）、人才培育與引進、以及開放的生態系統被視為致勝關鍵。在出口管制方面，他們認為需在國家安全與美國技術全球擴散之間取得平衡，確保美國的AI技術棧成為全球標準。他們也對AI的潛在社會影響（如就業、偏見）表示關注，並強調企業與政府合作的重要性。

聽證會全文 ( by downsub )

Good morning. The Senate Committee on

Commerce, Science, and Transportation is

called to order. Welcome to our

witnesses. Thank you for joining us this

morning.

In the last two years, AI has brought

the United States and the world to a

critical inflection point. AI may be a

technology as transformative as the

internet or even more so. It has

unleashed a new global industrial

revolution with the potential to unlock

opportunities that improve our quality

of life, create jobs, and stimulate

economic growth. The country that leads

in

AI will shape the 21st century global

order. As a matter of economic security,

as a matter of national

security, America has to beat China in

the AI race. China has made AI central

to its national strategy. And China aims

to lead the world in AI by 2030,

investing heavily in AI adoption across

industries like manufacturing and

defense.

In this race, the United States is

facing a fork in the road. Do we go down

the path that embraces our history of

entrepreneurial freedom and

technological

innovation or do we adopt the command

and control policies of

Europe? I would suggest that Congress

draw on the lessons we can learn from

the dawn of the internet. In the early

1990s, Washington embraced the internet

and explicitly adopted a style of

regulation that was

intentionally and

decisively light touch.

Congress chose to deregulate under the

Telecommunications Act of

1996, while President Clinton pursued

tariff agreements and treaties that

protected America's intellectual

property and technological

exports. Further, in 1998, Congress

enacted a 10-year internet tax

moratorum so that state laws wouldn't

bulcanize and styy the promise of

e-commerce.

The results of these decisions were

extraordinary. I made a lot of money. By

2000, the United States has recorded

five straight years of historic highs in

productivity gains and investment

growth. Hundreds of thousands of new

jobs were created and the United States

became a top tech exporter with massive

sums of private investment pouring into

the US digital economy. By

contrast, EU countries pursued a series

of heavy-handed

regulations that proved enormously

costly. In

1993, the United States and

Europe had economies virtually identical

in

size. Today, the American economy is

more than 50% larger than Europe's.

The drivers of

that are tech and the shale

revolution. Those two comprise virtually

the

entirety of that massive growth o over

Europe. According to one EU Commission

report, only 6% of global AI startup

funding flows to EU firms.

6%. That is onetenth of the amount that

is going to American companies.

The

report directly blames this yawning

chasm on the EU's nasty regulatory

approach. And yet, the Biden

administration, for inexplicable

reasons, tried to align AI policy with

the EU to adopt their failed policies.

President Biden's sweeping AI executive

order, the longest executive order in

American

history, cast AI as dangerous and

opaque,

laying the groundwork for audits, for

risk assessments, and regulatory

certifications.

Biden's approach inspired similar

efforts in state legislatures across the

country, threatening to burden startups,

developers, and AI users with heavy

compliance

costs. Some of my colleagues suggest

that a friendlier version of the Biden

approach makes sense. They want a

testing regime to guard against AI quote

discrimination and have government

agencies provide quote guidance

documents, seemingly something out of

Orwell that will usher in what they call

best

practices. As if AI engineers lack the

intelligence to res responsibly build AI

without the bureaucrats.

Many in the

industry

foolishly have supported such

paternalism. Harmful regulations take

many forms. Biden's misguided midnight

AI diffusion rule on chips and model

weights would have crippled American

tech companies ability to sell AI to the

world. The Biden plan would have handed

over key markets to China.

We should want foreign countries,

particularly our our allies, to buy

American. I vocally opposed this rule

for for months and indeed the ranking

member and I together urged the Biden

administration not to adopt it and I'm

very pleased that President Trump has

now confirmed he plans to rescend it.

All of this busy body bureaucracy,

whether Biden's industrial policy on

chip exports or industry and regulator

approved guidance

documents, is a wolf in sheep's

clothing. To lead an AI, the United

States cannot allow regulation, even the

supposedly benign kind, to choke

innovation or adoption. American

dominance in AI depends on two factors.

Innovation and adoption. Innovation

drives breakthroughs and global

competitiveness. Adoption ensures that

these tools empower American workers and

businesses, enabling the United States

to become the world's leading adopter

and exporter of AI. Thankfully,

President Trump has largely reversed

Biden's misguided AI agenda.

In fact, I think AI was a sleeper issue

in this last elections. Americans wanted

to see President Trump and Republicans

and indeed all senators champion AI

policies focused on innovation and

adoption. The contrast has been

astounding. This year, there have been

over $1

trillion of new AI projects, including

major investments in Texas, like the

coreweave data center in Plano and the

$500 billion project Stargate in Abalene

by Open AI and Oracle and others.

Adopting a light touch regulatory style

for AI will require Congress to work

alongside the president, just as

Congress did with President Clinton. We

need to advance legislation that

promotes long-term AI growth and

innovation. That's why I will soon

release a new bill that creates a

regulatory sandbox for AI modeled on the

approach taken by Congress and President

Clinton at the dawn of the internet that

will remove barriers to AI adoption pres

prevent needless state

overregulation and allow the AI supply

chain to rapidly grow here in the United

States. That's how we'll accelerate

economic growth, secure US dominance in

AI, and beat China. And with that, I

turn to the rank ranking member

Campwell. Thank you, Mr. Chairman. Uh

thank you for this hearing, and welcome

to the witnesses before us, Mr. Alman,

Dr. Sue, Mr. Integrator, and Mr. Smith.

It's a great pleasure to have all of you

here, but it's especially prideful

moment for the Pacific Northwest to have

Mr. Smith and Mr. Altman here both

representing an open AI approach. By

that I mean a approach where we want to

win against China and a closed system by

making sure that what is developed here

in the United States and around the

globe is an architecture where the

United States wins and is open. To do

that, we need to focus in winning on

computing power, on algorithms, and on

robust data sources. All of that will be

key. Personally, I believe a continued

investment in NSF helps in all of those

areas as a good public private

partnership with the industry that's

represented here today. I'm so proud

that we passed the Chips and Science Act

because the Chips and Science Act also

set a foundation for investing in the

United States of America and bringing

more of the supply chain back to the

United States of America to build on a

future leadership that we already have I

believe in the computing power. But we

also need to understand that we have to

move forward on the chips act like the

University of Washington $10 million

grant on multi-design sets for chips.

The very large scale integrated designs

I'm sure that Dr. Sue will tell us about

today. But the fact that the United

States has to continue to lead on the

future designs and the implementation of

that also requires us to be very smart

about data centers, about sources of

electricity and how we're going to build

that supply that could be up to 12% of

electricity demand in the very near

future. So, how do we do that? I've

noticed in each of your testimonies,

you've all explained this, but I'm also

very proud that Microsoft has already

signed an agreement with one company,

Fusion Energy, in Everett, Washington

for a power source supply. Maybe Mr.

Alman in his testimony will talk about

this, but that they hope to get very

near future energy source from that. So

clearly the United States leading on

electricity and development. So, Mr.

Smith, very much appreciate in your

testimony the accentuation on the fact

that the United States of America needs

hundreds of thousands of new

electricians. Something we should all

want to get behind. The fact that having

electricity and the electricians and the

data source centers here in the United

States and in other places will be key.

While I want to see us move forward, as

the uh chairman said, we signed a letter

saying we needed a broader support for

export controls. I want to be clear,

export controls are not a trade

strategy. They are not a backpocket

issue that the president of the United

States whips out in trade negotiations.

We are going to move fast because we are

going to set standards. I believe those

standards should be encouraging very

broad distribution of US manufactured

and made AI chips and technology and

that we're asking our partners overseas

to comply with the rules that we

establish. Things like making sure that

there is no circumvention of the supply

that somehow gets into China's hands.

making sure that we have access and

making sure that we can verify on that

and also making sure that US data

companies and cloud-based companies are

allowed to be in that market. We should

not be going to markets overseas only to

have them tell us that organizations

with cloud services from the US would

not be allowed. This I believe would be

a robust

uh initiative on getting US AI chips and

US AI open systems dominated around the

globe. Why do we need to move fast? We

need to move fast because if we don't,

we are looking at another Huawei,

another instance where the United States

is behind and also saying we should tear

out this system that now we don't like

for lots of reasons and backdoor

policies. So, I'm all for winning. That

is why we passed the Chips and Science

Act. I'm all for winning and that is why

we have passed seven bills out of this

committee last year that kind of got

stuck in the lame duck. I think the

chairman of the committee wasn't ready

to move forward in negotiations with the

House and Senate on those seven bills.

But those bills, a bill between myself

and Senator Young on the uh Institute

for uh standards, NIS standards, which I

think we still need to do, my colleague

and I, Moran, on education and

scholarships, small business, and uh the

bill by my colleague here, Senators

Clolobachar and Thun, which was also

related to the Nest standards. So, we

had an opportunity a year ago to move

fast. we didn't do it. So, let's do this

now. Let's get together and figure this

out. The faster the United States moves

now. I like this great uh Paul Ror quote

which was about collaboration is the

next phase of innovation. If we don't

collaborate here, if we throw down on

politics instead of getting the policy

right, we won't move fast. Let's allow

these people to do what they do best and

let's make sure the United States has

the right policies in place so that our

open AI standard wins the day. Thank

you, Mr. Chairman.

Thank you. Uh I'd now like to introduce

our witnesses for today. Each of our

witnesses and their companies represent

critical parts of the AI infrastructure,

hardware, and software supply chain. Our

first witness is Sam Alman, the

co-founder and CEO of Open AI. Open AAI

is one of the world's most advanced AI

companies, known best for its chat GPT

product. Our second witness is Lisa Sue,

the chair and CEO of Advanced Micro

Devices AMD. AMD develops high

performance processors, graphic chips,

and AI accelerators that power

artificial

intelligence. And Dr. Sue is also a

Texan. Our third witness today is

Michael and Trader, the CEO and

co-founder of Coreeave, an AI

hyperscaler. Coreweave is the world's

largest purpose-built AI cloud platform.

And our final witness is Brad Smith, the

vice chair and president of Microsoft. I

believe everyone is familiar with his

company. Uh Mr. Altman, you are

recognized for your opening statement.

if you could turn on the volume. Sorry

about that. And and I do enjoy telling

techies how to operate the tech. Pretty

embarrassing that I couldn't figure that

out. Anyway, thank you, Chairman. Thank

you, Ricky Member Campell. Thank you,

all senators and fellow panelists. Uh

it's a real honor to be here. I I was

here about two years ago, and at that

time, Chad GBT had recently launched. It

was a curiosity in the world. People

weren't sure what it was going to mean,

what it was going to be used for. Um

today, uh we've we've made significant

progress. Chacht is used by more than

500 million people a week. Uh I just saw

yesterday that it according to Similar

Web, it's now the fifth biggest website

on the internet globally. Um growing

very quickly, but most of all, it's

being used in really important ways.

It's significantly increasing

productivity. We hear scientists say

they're two or three times more

productive than they could be before. We

hear people, they're getting uh medical

advice or learning in ways they couldn't

before. And it's really it's it's no

longer this thing that was going to come

uh in the future, but it's a it's here

now and people are really using it.

We're very proud um to be one of the

leaders of this. We're very proud that

America is leading in AI uh so

significantly and I think that's

critical what uh what Senator Cruz said

about the importance

of innovation in America and that we

have the what happened with the internet

we have happen again. I believe this

will be at least as big as the internet

maybe bigger. um that needs to happen.

For that to happen, investment in

infrastructure is critical. I believe

the next decade will be about abundant

intelligence and abundant energy. Um

making sure that those that America

leads in both of those that we are able

to usher in these dual revolutions that

will change the world we live in, I

think, in incredibly positive ways is

critical. I got to go to Abalene, Texas

yesterday, uh where we're bu building

out what will be the largest AI training

facility in the world. It's coming along

beautifully. Uh super exciting to see.

We need a lot more of that. There's a

whole sort of AI factory, like a supply

chain of energy, chips, standing up data

centers, building the racks, and more.

We've got to do that really well in the

US so that we can continue to innovate,

continue to lead, um, and continue to

sort of shape this revolution. Speaking

of that, um, I was very inspired by what

Chairman Cruz said. So, I'd like to

deviate from script here and tell a

story. In my prepared written testimony,

I covered the basics. Um, so if it's

okay, I'd love to tell you a story. Uh,

I I grew up in St. Louis and I was a

computer nerd and it was the time of the

internet boom and I thought it was the

coolest thing ever. Um, we kind of lived

in this beautiful old brick house in

this uh, suburb of St. Louis and I lived

in the attic and I had this computer and

I would stay up all night and I would

learn to program and I got to kind of

use the internet and it was like a crazy

time of tons of innovation. All sorts of

stuff was happening. Um, it was amazing

and it was all happening here. All the

internet companies were in the US. I

used a Mac that was built here. I used

chips that were started, you know, near

where I now live. Uh, and I learned

about computers. I thought it was the

coolest thing ever. And I can draw a

straight line from that experience to

founding OpenAI and getting to work on

companies like Helium. The spirit of

American innovation and

um, supportive entrepreneurship. I I

don't think the internet could have

happened anywhere else. And if that

didn't happen, I don't think the AI

revolution would have happened here. Um,

I I am a child of the internet

revolution. I have the great honor to be

one of the parents of the many parents

of the AI revolution. And I think it is

no accident that that's happening in

America again and again and again. But

we need to make sure that we build our

systems and that we set our policy in a

way where that continues to happen. Um,

I think this is magic. I don't want to

live in Europe either. Uh, I think

America is just an incredible and

special thing and it will not only be

the place where the AI revolution

happens, but all the revolutions after.

I was home visiting St. Louis recently,

drove by our old house and I kind of

like it was at night and I looked up and

in that like top floor window, the light

was on and I thought, you know,

hopefully there's some kid in there

staying up late at night playing with

chatbt, figuring out how he or she is

going to start whatever company comes

next and whatever the next thing is

after I will happen here too. Um that is

that is to me the magic of this country.

It's incredibly personally important and

I hope it keeps going. Thank you very

much for having me.

Thank you. Uh Dr. Sue,

Chairman Cruz, Ranking Member Canwell,

members of the committee. It is a real

honor to be here on such an important

topic. I am chair and CEO of AMD. We are

a US headquartered semiconductor company

founded 56 years ago and we build high

performance computing chips for the

modern economy. Every day, billions of

people rely on our products and services

powered by our technologies. But our

chips are also extremely important to

support the critical missions including

powering defense systems and secure

communications as well as enabling

breakthrough scientific research. Um, I

have to say our proudest moments though

are when we see amazing public private

partnerships and our work in

supercomputing is an example of that.

Through more than a decade of

partnership with the Department of

Energy, AMD now powers the two fastest

supercomputers in the world. One uh that

is housed at Oakidge National Labs that

was put into place in 2021 and the other

um at Lawrence Liverour National Labs

that was just recently uh put into

commission uh late last year. These

systems are really critical from a

national infrastructure standpoint and

solve uh many many um large research

issues as well as national um security

and scientific leadership. Now in terms

of AI, you know, there's so much that's

been stated about AI. Um I really want

to thank um Chairman Cruz and Ranking

Member Kentwell for having this hearing.

I think it is a wonderful opportunity to

talk about how we win. Um AI is truly

the most transformative technology of

our time. The United States leads today.

But what I would like to say is it is a

race. Leadership is absolutely not

guaranteed. Uh it's a global race that

will shape the outcome of national

security and economic prosperity for

many decades to come. Now maintaining

our lead actually requires excellence at

every layer of the stack. So I'm really

honored to be here with my panelists as

well. We have deep partnerships with

Microsoft and OpenAI that demonstrate

how you need silicon, you need software,

you need systems and uh really the

application layer to be successful. Now

in terms of what to do, I thought about

what would be the most important things

to say today and I put them in, you

know, five categories. Um I think the

first and probably the foremost is we

must continue to run faster. Uh this is

a race and the race does not stand

still. Nobody in the world stands still.

uh we lead today because of the bold

decisions that we've made and because of

the innovation uh economy that we have

but we need to continue to run faster

and that means ensuring that we have

computing available. I think Sam's story

about Aene is an excellent example of

how when you allow uh the uh computing

infrastructure to expand at the rate and

pace that um the private sector wants

you actually make a tremendous progress.

I would also like to mention the

importance of open ecosystems. I think

open ecosystems are really a cornerstone

of US leadership and that allows um you

know frankly ideas to come from

everywhere and every part of the um

innovation cycle reducing barriers to

entry and strengthening uh security as

well as creating um frankly a

competitive marketplace for ideas. Um

third you know we are very um happy to

see the focus on a robust domestic

supply chain. For us in the

semiconductor world, we used to not get

so much attention. Now we get a lot of

attention uh thanks to uh the importance

of chips. And you know the fact is we

need more uh manufacturing in the US. Uh

the efforts so far have made good

progress but there's a lot more that can

be done and that should be done in

public uh private partnership. Um fourth

we must invest in talent. you know,

frankly, the United States should be the

best place uh to study AI, to work in AI

to really uh move forward all of the

innovations that we need. And I think

again this can also be done in

significant public private partnership.

And then fifth of course in the area of

export controls um we must we totally

understand as an industry the importance

of national security and that is you

know without that goes without saying as

a US company but we also want to ensure

um as chairman Cruz and ranking member

Kentwell stated it is important to have

widespread adoption of US technologies.

We lead today because we have the best

technology. However, if we're not able

to um you know fully uh have our

technology adopted in the rest of the

world, there will be other technologies

that will come to play. They may not be

as good as we are today, but frankly um

usage uh really spurs um innovation. And

this is something that we certainly need

to work with in uh public private

partnership. And I would frankly end by

saying, you know, like Sam, I had a

computer uh when I was growing up. Um I

grew up in New York. Um I'm a little

older than Sam. So my first computer was

a Commodore 64 and then I graduated to

the Apple 2. Uh but the fact is um this

is the best place to do um computing

innovation in the world. We wanted to

stay that way with uh really a very rich

and broad um ecosystem. So thank you

again for the opportunity uh to be here

today.

And I had an Apple 2 as well with a shoe

box of floppy discs and somehow I ended

up taking a wrong turn and ending up in

politics instead. Uh Mr. and

Trader I started out with a Vic 20. Um

uh Chairman Cruz, ranking member uh

Canwell and distinguished members of the

committee. Thank you for the opportunity

to testify today. I am honored to appear

alongside my industry colleagues and

partners. Uh my name is Michael and

Trader. I am the co-founder and CEO of

Cororeweave, founded seven years ago. Uh

Cororeweave started like many innovative

ventures humbly in a garage

experimenting initially with graphics

processing units or GPUs for

cryptocurrency mining. Uh recognizing

the transformational potential, we

pivoted to support powerful AI

applications, dramatically scaling the

vision uh and operation. Today,

Cororeweave stands at the forefront of

America's AI infrastructure revolution,

operating more than 30 data centers

across 15 states. We manage more than

250,000 GPUs, currently using 360

megawatts of power. Uh over two short

years, our revenue has surged by 12,000%

reaching 1.9 billion in 2024.

As a result of this progress,

Cororeweave became publicly traded

company on March 28th of

2025. Corweave ratchet rapid growth is a

testimony not only to the technology but

also to the surging global demand for

advanced AI infrastructure. Our

infrastructure enables American

businesses to rapidly translate AI

aspirations

uh uh into impactful economic realities.

By empowering companies to accelerate

innovation, we're fueling America's

competitive edge while improving

productivity and

prosperity. Modern AI requires

specialized infrastructure,

purpose-built computing capabilities

that surpass traditional cloud computing

in scale and performance. Today's

generalpurpose cloud that was built to

support and scale the complexity of AI

workloads. We cannot run a 21st century

economy on the 20th century's

infrastructure. AI workloads involve

trillions of simultaneous calculations

demanding unprecedented computing power,

advanced cooling systems, cutting edge

chip technology,

ultra high speeded networks, and

accelerated storage. Since 2018, the

computing power necessary for advanced

AI models has multiplied approximately a

100,000fold.

At Cororeweave, our facilities symbolize

America's great tradition of innovation.

Our data centers, built, maintained, and

staffed by skilled American workers,

embody how modern technology not only

stimulates economic growth and enhances

national security, but also improves

humans lives. We are at a critical

juncture in the global AI competition.

The nation that leads in infrastructure

will set the global economic agenda and

shape human outcomes for decades. Our

largest competitor, China, recognizes

the stakes and is expending significant

resources to strengthen their

position. I want to focus on four

elements of policy that will help

determine whether the US secures its

leadership role in the AI race. First,

strategic investment stability. AI

infrastructure is deeply capital

intensive and requires a significant

level of coordination across industry

stakeholders. Stable, predictable policy

frameworks, secure supply chains, and

regulatory environments that foster

innovation are crucial. Policymakers

must provide clear and consistent policy

and regulations across all jurisdictions

that enables long-term investment and

rapid scaling of AI

technology. Second, energy

infrastructure development. To support

the rapid deployment of AI

infrastructure, America must ensure

abundant and affordable supplies of

energy. Careful reforms in permitting

and regulatory process are necessary to

accelerate infrastructure projects,

facilitate more rapid construction,

interconnections, and energy for data

centers. Third is global market access.

Maintaining America's leadership also

means ensuring our technology is fair

access to global markets. Export

controls and trade agreements can be

calibrated to both address national

security risks and support global

diffusion of American AI technology. And

finally, public private partnerships and

workforce development. America's unique

advantage in the AI is enhanced by our

powerful tradition of public private

partnership. Corweave is proud to

co-ound the New Jersey AI hub with

Microsoft Princeton University and the

New York and the New Jersey Economic

Development Initiative. Initiatives like

this develop critical workforce skills,

foster innovation, and ensure economic

and economies and communities are

prepared for the AIdriven future.

America stands ready to lead the AI

revolution, which will bring enormous

benefits. It is a rare moment in time

that we must meet. If government,

industry, and all affected parties work

together, the United States can win this

race and seize the vast opportunity

ahead of us. Thank you again for the

opportunity to testify. I look forward

to answering your questions. Thank you,

Mr. Smith.

Chairman Cruz, Ranking Member Canwell,

members of the committee, thank you for

the opportunity to be here today. Um,

let me just build on what my three

colleagues have said and and offer a few

thoughts. Uh, the first is I just wanted

to refer to the chart on this easel that

shows the AI tech stack that was also in

my written testimony. It makes a simple

but I think important point.

We're all in this together. If the

United States is going to succeed in

leading the world in AI, it requires

infrastructure. It requires success at

the platform level. It requires people

who create applications. Interestingly,

we at Microsoft get to work with all

three of these leaders and their

companies. Our success, each of our

success depends on each other's success.

And what's true of the four of us is

true when you look across the country

and around the world at open-source

developers, people who are building

power plants, electricians and pipe

fitters who are going to work every

single day. So what do we need from the

Congress and the country in order to

succeed? I think it's three things. I

described them in my written testimony.

First, as Chairman Cruz said, we need

innovation. Innovation will go faster

with, as Sam said, more infrastructure,

faster

permitting, more electricians. We need

more innovation fueled, as ranking

member Canwell said, by support from our

universities and the federal agencies

that support basic research across the

country. One of this country's crown

jewels. We also need, as Chairman Cruz

said, faster adoption, what people refer

to as AI

diffusion, the ability to put AI to work

across every part of the American

economy to boost productivity, to boost

economic growth, to enable people to

innovate in their work. And the number

one ingredient for that, history shows

time and time again, is skilling,

investing in education. And finally, we

need to export. If America is going to

lead the world, we need to connect with

the world. We need to remember, I

believe always, that as a country, only

four and a half% of the world's people

live in the United States of America.

Our global leadership relies on our

ability to serve the world with the

right approach to export controls and

always, especially in technology, in our

ability to sustain the trust of the rest

of the world. Ultimately, I think people

who take the time, if they take the time

to watch or read about this hearing, may

wonder, what is this all

about? What are we at this table trying

to do? What do these two letters AI

really mean to them? Are we who are

working in this industry trying to build

machines that are better than people? Or

are we trying to build machines that

will help people become better?

emphatically it is and needs to be the

latter. Are we trying to build machines

that will outperform people in all the

jobs that they do today? Or are we

trying to build machines that will help

people pursue better jobs and even more

interesting careers in the

future? Indisputably, it needs to be the

second, not the first. And I believe

that is what we are and can do together.

As somebody who's now spent almost 32

years in this industry, there are two

things that always strike me. The first

probably won't surprise you. Never

underestimate what technology can do,

how quickly it can move, what it can

accomplish. But the second is one that I

think is too seldom discussed, even

though every day it stares us in the

face.

Never estimate what people can do. Never

underestimate human ambition. Never

underestimate what a person can do. If

given a better technology tool and the

ability to learn how to put it to use.

That's the story of this industry. It's

the story of the country. It is, as you

heard, the story of Sam Alman. Not

everybody becomes a Sam Alman or a

Satcha Nadella or a Bill Gates.

Everybody deserves the opportunity to

try. Tonight across America, whether

it's the attic of a house or the

basement or just an everyday

bedroom. There are kids with computers,

with phones, with access to the

internet, and now the ability to put AI

to work. Let's invest in their

education. Let's invest in the skills

that the American public needs. Let's

then invest in creating the future that

the American public deserves. Thank you.

Well, thank you witnesses for your

testimony and uh I'll start off with the

first round of questions and and move

Don Das to our uh ranking member here.

Thank you for your uh testimony.

Certainly makes me sleep better at night

worried about Terminator and Skynet

coming after us knowing that you guys

are behind the wheel. But uh in five

words or less, starting with you, Mr.

Smith, what are the first what are the

five words you need to see from our

government to make sure we win this AI

race?

Um, more

electricians, that's two

words, broader AI education and no using

chat. GPT is a phone a friend.

Thank you. Um I would say that we need

to focus on uh streamlining the ability

to build large

things policies to help us run faster in

the innovation race.

Allow supply chain sensible

policy. That was

good. So what I hear there is is

something pretty similar to to uh the

races we've won before. uh nuclear

energy for example, you know, the

Germans and Austrians really led the

innovation around that, but we won the

race because we put a massive government

effort collaborating with our

universities and others to win that

race. Uh space, you know, the Soviets

put the first satellite up, put put the

f put the first man in space, but we won

the space race because we adopted a

framework to ensure that we won u

aviation, automobiles, etc.

So what I what I hear from you is is you

you do need support from our government,

but you also need the government to stay

out of your way so you can innovate and

win this

race. How do we incentivize companies to

do business here in America to make sure

we win this race in America and America

leads not just China, but other

non-state actors, too? I mean, I think

that the scariest thing about AI from a

capability standpoint is it doesn't have

to be a state actor to win this race.

It's not like nuclear engine. It's not

like space technology. I mean, this a

non-state actor could just as easily win

this race and wield more power than

anyone else. So, how do we encourage

innovators investment to happen here in

America to ensure we win this race? Mr.

Alman, you want to start? We were

honored to announce back in January uh

project Stargate a 500 billion

investment in United States

infrastructure. Uh that is now well

underway. As I mentioned, getting to see

it yesterday in Abalene. Uh the first

site was incredible. We need a lot more

of that. We need

uh certainty on the ability to build out

this entire supply chain, build the data

centers, permit the electricity. We'd

love to bring chip production here,

network production here, server rack

production here. Um, and I think the

world does want to invest. We have a lot

of global investment flowing into the US

to do this. We also want to make sure

that other countries are able to build

with our technology, use our models um

and sort of like be in our orbit and you

know use US diffusion of technology

here. So that's really important. Uh we

need to make sure that the highest

skilled researchers that want to come

work at US companies can come here and

do that. Uh we need

to we need to make sure that companies

like OpenAI and others have legal

clarity on how we're going to operate.

Of course, there will be rules. Of

course, there need to be some

guardrails. This is a very impactful

technology, but we need to be able to be

competitive globally. We need to be able

to train. We need to be able to

understand how we're going to offer

services and sort of where the rules of

the road are going to be. Uh so clarity

there and and I think an approach like

the internet which did lead to

flourishing uh of this country in a in a

very big way. We need that again.

Dr. Sue, I would add I think computing

is a foundation to all of this. uh we

want to have more compute built in the

US by US companies and ensure that we

have a great environment for that. We

want to ensure that our technology um

around the world is also used uh broadly

and in the right ways. So I think the uh

conversation about export controls and

rules should just be simple, easy to

follow, easy to enforce and enable uh US

AI platforms to be the foundation. And

then certainly the comments around uh

bringing manufacturing back home and

ensuring that we have the right talent

base are all extremely um important

elements of of that. Are companies

weighing doing business in AI in America

verse China? Are the companies making

that sideby-side comparison?

I think if you look across the world um

there are you know countries and

companies that will um ask those

questions. you know if it's hard to

obtain US technology although US

technology is the best if it's hard to

obtain then you know there's a hunger

for AI and they will choose what is

available and if China is available that

will um you know certainly be a outcome

that we would not like to see

well I think I hear the words

infrastructure electricians universities

regulatory framework and I think those

are things we can help with I hear words

like innovation and talent and I say I

hear Dr. pursue run faster. Those aren't

things a government can't manufacture

talent. We can't make you run faster,

but we can give you the tools to do

that. And I think it's time that that we

we create a framework so that you have

the tools you need to win this race

because you're going to be the ones that

win it, not us. Thank you for testimony

and recommen.

Thank you, Mr. Chairman. Uh I'd like to

continue that same theme generally about

competitiveness. Do we need uh NIS to

set standards? If you could just yes or

no and just go down the line.

I don't think we need it. It can be

helpful.

Yes.

Yes.

Yes. Okay. So, in the context of uh what

we're talking about here, we're really

just talking I don't know uh Mr. Smith

or Mr. Integrator or Dr. pursue any the

issue here is if we want to move fast we

want to create just like with

electricity the standards by which we

want to move fast here I would just call

it code for code is what we want right

we want NIS to do something in the

standard setting that will allow us to

move much faster is that is that right

either Mr. Smith or Mr. integrator. What

I what I would say is this. First of

all, um NIST is where standards go to be

adopted, but it's not necessarily where

they first go to be created. So, we've

got Thank you for that clarity. We're

talking about a industry uh it e lots of

different organizations industry input

and then they're adopted. So, yes, let's

clarify that. Let's clarify that. I

think that's the way it works. Yes. And

but you think we need to do that

particularly if the United States wants

to lead. We will need industry

standards. We will need American

adoption of standards and you are right.

We will need US efforts to really ensure

that the world buys into these

standards. Okay. Mr. Integrator,

I I think it's important that when

you're working with standards, what that

allows for is a common vocabulary which

allows for acceleration. And so uh to

the extent that we can step into that

role and establish uh uh touch points

where everyone can agree on specific

things that will lead to uh uh an

acceleration both domestically and and

and abroad and um and I I don't know if

you know drilling down more on what you

think those are but in in general you

know when I think about the internet and

HTTP or HTML or any of the number TCP IP

we're talking about things that allowed

us to move faster and getting those

standards established uh helped us do

that. On the export issue uh Mr.

Intertor uh the issue of cloud sources

shouldn't be left out if if we say let's

go with Malaysia. Malaysia is going to

tell us that they can certify that

there's no, you know, diversion of these

ships to Asia, you know, to China and we

basically have a way that we can make

sure that that this is understood and

monitored. Then we also want accessed,

right? We want access by US companies.

Yeah, I think Lisa's point was

excellent, right? Um, at the end of the

day, um, the world wants to be able to

build and deploy artificial intelligence

in a in a very broad way. And if we, you

know, nature horses a vacuum, if we do

not step into that role, other

technology will step in that role. If it

is suboptimal, so be it. It's better to

have something that is suboptimal than

have nothing. And so that is what well

we don't we don't want a reoccurrence of

a Huawei that develops faster and then

has a government backdoor and then we

all have to raise opposition. I'm I'm

for a tech NATO. I'm for the five most

sophisticated democracies and tech

nations setting the rules of the road

and saying this is who you should buy

from. Don't buy from anybody else who

has a government backdoor. Not a good

idea. So that's how we get leverage. You

know, I'm I'm not so hot on the

president's tariff agenda for this very

reason because we're not building the

alliances. We're creating the enemies.

And what I want to do is get the supply

chain here, get the semiconductor flow

here, lower the cost, and go as fast as

we can. Yeah, I I I I agree with that. I

don't think that that's that's uh

um I don't think anybody's not going to

agree with that, right? I think that's

an excellent objective. I just think

that

um what will happen beyond the five

NATO companies is that there will be a

demand for artificial intelligence and

they will proceed with what they can

proceed with. Dr. Sue, what is your view

of this about how we win, how we protect

our objectives, but we're more

aggressive on the on the export

strategy? Well, I I think there is a

clear recognition that we need an export

strategy and so having you know having

this conversation is uh is very

important and from our perspective the

idea is to ensure that our allies and

frankly I use allies in the very

broadest sense uh get access to the

great American technology that we have

with the appropriate uh controls in

place and I think you can do both. uh to

your earlier uh comment uh ranking

member Kentwell about uh the need to

have uh US technologies in those

countries. I think I think those

countries are actually very interested

in doing that because we do have the

best technology today and using that to

really build this broad AI ecosystem um

is um is really our opportunity. I

agree. Thank you so much.

The senior senator from Ohio. Thank you,

Chairman

Chihi. Make sure uh Senator Cruz heard

that one. Uh so, first of all, thank you

for being here and uh taking the time.

If I could um just real quickly just

confirm that I've heard what you said uh

pretty unanimously, which is we need

dramatically more power generation in

this country. Is that correct? All

right.

So, Dr. Sue, you you just recently uh uh

uh did a partnership with TSMC to

manufacture your chips here in America.

Thank you. I think it's a little bit

long overdue. I wish you had uh we had

done more of that earlier. Uh those uh

semiconductor uh fabs um high energy

users.

Uh thank you, Senator. We are very

pleased with our um efforts together

with the the government on bringing more

manufacturing back to the United States.

uh to your question uh certainly

semiconductor manufacturing uh plants

are high energy users and we do need

more power for both manufacturing as

well as for data centers as you

mentioned and and without chips this

just doesn't work like if we don't have

the highest performance chips made here

in the United States this is not going

to happen here correct we we absolutely

need the highest performing chips and we

also need um the entire ecosystem for

chip manufacturing so wafers are one

piece but there are many other pieces as

well and are those chips powered by

solar solar power and windmills. Uh,

today they're not, but I think there are

opportunities to certainly. So, so do

you think it's outrageous that last year

because of the policies of the Biden

administration that 90% of new power

generation in this country was windmills

and solar panels and we absolutely

kneecapped American energy? We have

a,000 years of natural gas sitting in

Pennsylvania, Ohio, and West Virginia.

And yet 90% of power generation in this

country last year was solar panels and

windmills. Does that make this country

more competitive or less competitive?

Anybody can jump into that one that

wants to answer

that. Let me say two things. One, you're

right. We need more electricity. I think

our industry, it's worth remembering, is

only going to account for 15% of the

total additional electricity the country

is going to need. We are going to need

electricity from a variety of sources.

Today in the United States, 56% of our

electricity comes from carbon. 44% comes

from carbon-f free energy, meaning

nuclear, wind, or solar. We need a

broad-based approach and we need a

diversity. But again, 90%

was energy that's not affordable. It's

not abundant and it's not reliable. Let

me just shift gears. Uh Mr. Alman, thank

you for first of all creating your

platform in an open basis and agreeing

to stick to the principles of nonprofit

status. I think that's very important.

Do you think that uh the uh internet age

did a good job between the beginning of

the 90s through the 2000s of protecting

children?

I would say not particularly. Yeah. And

you're a new father, correct? Yes.

Congratulations. Thank you very much.

He's doing well. He is. It's the most

amazing thing ever. Yeah. I don't think

you want your best uh your child's best

friend to be an AI bot. I do not. Uh so

what can we do? How how can we work

together to protect children?

We've talked a lot about some of the

things we're doing here. We're trying to

learn the lessons of uh previous

generation and you know that's kind of

the way it goes. You people make

mistakes and you do it better next time.

Uh one thing we say a lot internally is

we want to treat our adult users like

adults. We want to give them a lot of

flexibility. We want to let them use the

service with a with a lot of freedom. Um

and for children there needs to be a

much higher level of protection which

means the service won't do things uh

that they might want. Now, we're still

early, so sometimes people say, "Oh,

you're being too strict on the rules."

And it's just we can't perfectly like

tell this, but if we could draw a line

and if we knew for sure when a user was

a child or an adult, we would allow

adults to be much more permissive and

we'd have tighter tighter rules for

children.

So I think what I would ask is if you

could have your team commit to having

your teams work with our teams to make

certain that we put together the right

framework early on I think is may the

best way we can move forward because we

don't want to overregulate but we can't

repeat the mistakes of the internet and

social media era where children got

harmed. We'd be delighted to work with

you all. It's super important. Thank

you. Can I say one more thing what you

said? this idea of AI and social

relationships. I I think this is a new

thing that we need to pay a lot of

attention to. Um people are relying on

AI more and more for life advice, sort

of emotional support, that kind of

thing. It's it's a newer thing in recent

months, but I and I don't think it's all

bad, but I think we have to like

understand it and watch it very

carefully. All right. Thank you and

thank you for that commitment. It's very

appreciated. I've talked to your team

already. Good people. Great. U Mr. turn

to door. Uh real quickly, uh can you

talk about the intersection between the

importance of a robust stable coin

ecosystem here in America and how that

uh has a future with payments and how AI

will factor into that because I don't

think people see how this fits into the

broader puzzle.

Uh so thank you for the question and um

um we did start out as a cryptobased uh

company uh uh hobby that kind of got

away from us a little bit. Um, look, I I

think that uh uh stable coins uh crypto

uh AI they they share certain DNA in

common which is that they are uh

attempts to build into a future where

new technology will make things better

for uh society and there is a huge

potential for us to use stable coins,

crypto and AI in a combination for for

better outcomes. All right, thank you.

And that was the quickest coup since

1959.

[Laughter]

Senator Clolobachar. Thank you very

much, Senator Cruz. A lot of exciting

things with AI, especially from a state

uh like mine that's home to the Mayo

Clinic with the potential to uh unleash

scientific research while we've mapped

the human genome and we have rare

diseases that can be solved. So, there's

a lot of positive, but we all know, as

you've all expressed, uh there's

challenges that we need to get at with

permitting reform. I'm a big believer in

that energy development. Thank you, Mr.

Smith, for mentioning this with wind and

solar and the potential for more fusion

and nuclear, but wind and solar, the

price going down dramatically um in the

last few years. Um and to get there,

we're going to have to do a lot better.

Um, I think David Brooks put it the best

when he said, "I found it incredibly

hard to write about AI because it is

literally unknowable whether this

technology is leading us to heaven or

hell." Um, we wanted to lead us to

heaven. And I think we do that by making

sure we have some rules of the road in

place so it doesn't get stymied or set

backwards because of scams or because of

use uh by uh people who want to do us

harm. As mentioned by Senator Canwell,

Senator Thun and I have teamed up on

legislation to set up basic guard rails

for the riskiest non-defense

applications of AI. Uh, Mr. Alman, do

you agree that a riskbased approach to

regulation is the best way to place

necessary guard rails for AI without

stifling innovation? I do. That makes a

lot of sense to me. Okay. Thanks. And

did you figure that out in your attic?

No, that that was a more recent

discussion. Thank you. Very good. Just

want to make sure um um our uh bill

directs Mr. Smith the Commerce

Department to develop ways of educating

consumers on how to safely use AI

systems. Do you agree that consumers uh

need to be more educated? This was one

of your answers uh to your five words.

So I assume you do. Yes. And and I think

it's incumbent upon us as companies uh

and across the business community to

contribute to that education as well.

Okay. Very good. Back to you, Mr. Alman.

The uh Americans rely on AI as we know

increasingly on some high impact

problems to make them be able to trust

that uh we need to make sure that we can

trust the model outputs. Uh the New York

Times recently reported earlier this

week that AI hallucinations, new word to

me, uh where models generate incorrect

or misleading results are getting worse.

Um that's their words. uh what standards

or metrics does open AAI use to evaluate

the quality of its training data and

model model outputs for correctness?

On the whole, uh AI hallucinations are

getting much better. We have not solved

the problem entirely yet, but we've made

pretty remarkable progress over the last

few years. When we first launched Chat

GPT, um it would hallucinate things all

the time. This idea of robustness, being

sure you can trust the information.

We've made huge progress there. We site

sources. the models have gotten much

smarter. Um, a lot of people use these

systems all the time and we were worried

that if it was not 100, you know, 0%

accurate, which is still a challenge

with these systems, it would cause a

bunch of problems. But users are smart.

People understand, you know, what these

systems are good at, when to use them,

when not. And as that robustness

increases, which it which it will

continue to do, people will use it for

more and more things. Um but we've made

as an industry we've made pretty

remarkable progress in that direction

over the last couple of years. Well, I

know we'll be watching that. Another um

challenge that has been uh we've seen

and Senator Cruz worked and I worked on

a bill together uh for quite a while and

that's the take it down act. And that is

that we are increasingly uh seeing um

internet activity where kids looking for

a boyfriend or girlfriend maybe they put

out a real picture of themselves it ends

up being distributed at their school or

uh they somehow they someone tries to

scam them from financial gain or it's AI

as we've increasingly seen where it's

not even someone photos but someone puts

a fake uh body on there and we've had

about over 20 suicides in one year of

young people uh because they felt their

life was ruined because this was they

were going to be exposed in this way.

So, this bill we passed um and through

the Senate and the House um um the first

lady supported it and it's headed to the

president's desk. Could you talk about

how we can build models that can better

detect harmful deep fakes? Mr. Smith?

Yeah, I mean we're doing that. Open AAI

is doing that. A number of us are. And I

think the the goal is to you first

identify content that is generated by

AI. Uh and then often it is to identify

what kind of content is harmful. And I

think we've made a lot of strides in our

ability to do both of those things. Um

there's a lot of work that's going on

across the private sector and in

partnership with groups like NickMech to

then uh you collaboratively identify

that kind of content so it can be taken

down. Um, we've been doing this in some

ways for 25 years since the internet and

we're going to need to do more of it.

And on the issue, last question, Mr.

Chair, since the last one was about your

bill, I figured it's okay. Um, the, uh,

newspapers and you testified before the

Senate Judiciary Committee, uh, Mr.

Smith, about the bill, Senator Kennedy

and I had still think that there's an

issue here about uh, negotiating content

rates. We've seen some action recently

in Canada and other places. Um, can you

talk about those evolving dynamics with

AI developers and what's happening here

to make sure that uh content providers

and journalists get paid for their work?

Yeah, it's a complicated topic, but I'll

just say a couple things. First, I think

we should all want to see newspapers in

some for form flourish across the

country, including say rural counties

that increasingly have become news

deserts. newspapers have disappeared.

Second, and it's been the issue that we

discussed in the judiciary committee,

there should be an opportunity for

newspapers to get together and negotiate

collectively. We've supported that. That

will enable them to basically do better.

Um, third, every time there's new

technology, there is a new generation of

a copyright debate that is taking place

now. Some of it will probably be decided

by Congress, some by the courts. A lot

of it is also being addressed through

collaborative action. And we should hope

for all of these things to I'll just say

strike a balance. We want people to make

a living creating content and we want AI

to advance by having access to data.

Okay. Thanks. I'll ask other questions

on the record. Thank you, Mr. Chair.

Thank you. You know, Senator Clolobachar

asked whether AI will lead us to heaven

or hell. It reminded me of a famous

observation by Yale law professor Grant

Gilmore that in heaven there is no law

and the lion will lie down with the

lamb. In hell there is nothing but law

and due process is meticulously

observed. Let me ask you this and this

is to each of the four

witnesses. In the race for

AI, who's winning, America or

China? If the answer is America, how

close is China to us? And what do we do

to make sure the answer remains America

will win? Mr. Alman, we'll start with

you.

It is our it is our belief that the uh

American models including some models

from our company OpenAI and Google and

others are the best models in the world.

It's very hard to say how far ahead we

are, but I would say not a huge amount

of time. Um, and I think to continue

that leadership position and the

influence that that comes that comes

with that and the all of the incredible

benefits of the world using American

technology products and services. uh the

things that my colleagues have spoken

about here, the need to win in

infrastructure, sensible regulation that

does not slow us down, the sort of

spirit of innovation and

entrepreneurship that I think is a

uniquely American thing in the world. Um

none of this is rocket science. We just

need to keep doing the things that have

worked for so long and and not and not

make a silly mistake. Dr. Sue uh I'll

answer um in the uh realm of chips. I

would say America is um ahead in chips

today. We have the um the best AI

accelerators um in the world. Uh I think

China um although they have restrictions

given their ability to use advanced

technologies. Uh the one thing that's

very important for us all to remember is

there are multiple ways to do things.

You know, having the best chips is

great, but um even if you don't have the

best chips, you can get a lot done. So I

think this this conversation about how

far behind China is, they are certainly

catching up because there are many ways

to do things. I think relative to what

we can do uh I will continue to say uh

really ensure that our spirit of

innovation is um is allowed to work and

that is having um you know very

supportive government policies uh to do

that having very consistent policies and

allowing us to do what we do best which

is innovate at every layer of the stack.

Mr. Trader

Uh so I I I'll speak to it from the

physical infrastructure um and software

stack to deliver that. Um America is

ahead but it is the Achilles heel from

the perspective of the ability as I

started to to

better sorry about that. Uh so so the

the ability to build very large

solutions to the computing

infrastructure component of this is

uh an area that we're going to struggle

with from a permitting and building

large projects to be able to deliver the

the power to to allow uh those building

artificial intelligence to continue to

move as fast as they can in in the race

that we're in. Mr. Smith, I think the

United States has a lead today in what

is a close race and a race that will

likely remain close. The number one

factor that will define whether the

United States or China wins this race is

whose technology is most broadly adopted

in the rest of the world. This is a

global market and it will be defined as

technology markets typically are by

network effects. 18% of the people in

the world live in China. 4% live in the

United States. 78% live somewhere else.

The lesson from Huawei and 5G is whoever

gets there first will be difficult to

supplant. We need to export with the

right kinds of controls. We need to win

the trust of the rest of the world. We

need to have the financial architecture

that gets not only to the countries that

are industrialized but the nations say

across Africa where typically China and

Huawei have done so well.

So some of my colleagues have made

reference to standards as as something

that is desirable and I will say

standards is often code word for

regulations and indeed the EU stifling

standards

uh concerning the internet is what

killed tech in Europe. Uh we are seeing

now state legislators mimicking the EU

such as California's SB 1047 which

thankfully was overwhelmingly defeated

but would have created essentially a

California DMV for AI model

registration.

How harmful would it be to winning the

race for AI if America goes down goes

down the road of the EU and creates a

heavy-handed prior approval government

regulatory process for AI.

I I think that would be disastrous. Um

I to give a more specific answer to your

previous question which I think touches

on why it would be so bad. Um there

there are three key inputs to these AI

systems. There's compute, all the

infrastructure we're talking about.

There's algorithms that we all do

research on. Um and there's

data. If you don't have any one of

those, you cannot succeed in making the

best models. And as Brad said, the the

way for America to influence the world

here is to have the technology that

people most want to use and and most

adopt. The world uses iPhones and Google

and Microsoft products, and that's

wonderful. like that's how we have our

influence. We don't we don't want that

to stop happening. So systems that stop

us on any of these areas, you know, if

we if we have if we have rules about

what data we can train on that are not

competitive with the rest of the world,

uh then things can fall apart. If we are

not able to build the infrastructure and

particularly if we're not able to

manufacture the chips in this country,

the rules can fall apart. If we can't

build the products that people want that

naturally win in the market and I think

people do want to use American products

we can make them the best but if we're

prevented from doing that people will

use a better product made from somebody

else that doesn't have the sort of you

know that is not stymied in the same

way. So it

is I am nervous about standards being

set too early. I'm totally fine uh you

know with the position some of my

colleagues took that standards once the

industry figures out what they should be

it's fine for them to be adopted by a

government body and sort of made more

official but I believe the industry is

moving quickly towards figuring out the

right protocols and standards here and

we need the space to innovate and to

move quickly. So if each of you could

briefly answer that question because my

time's expired so I want to be

respectful of that. I I agree with the

comments that

um I agree and I would just say and I

think the point you're making is we have

to be very careful not to have these

pre-approval requirements including at

state levels because that would really

slow innovation in the

country. I I I think that uh a patchwork

of regulatory overlays will

uh cause friction in in the ability to

build and extend what we're doing.

Thank you. Um Senator Curtis shot.

Senator Shot, sorry. Apologies. No

problem, Chairman. Uh thank you for

being here. I just want to follow up on

on the chairman's question and a sort of

it may be an emerging consensus on the

committee. Okay. I don't think there's

anybody even on this side of the deis

that's proposing a sort of European

style

preapproval. I think there are some

people who would like to do nothing at

all in the regulatory space. But I think

most people understand that some guard

rails, those are the words that you use

uh Mr. Altman uh rules and guard rails

uh are necessary. Um, are you saying

that self-regulation is sufficient at

the current moment?

No, I I think some policy is good. Um, I

I think it is easy for it to go too far

and as I've learned more about how the

world works. I'm more afraid that it

could go too far and have really bad

consequences. But people want to use

products that are generally safe. You

know, when you get on an airplane, you

kind of don't think about doing the

safety testing yourself. if you're like

this is well maybe this is a bad time to

use the airplane example but you kind of

like want to just trust that you can get

on it's an excellent time to use the

airplane example um but but I think your

your point is exactly right is that um

look there is there is a race but we

need to understand what we're racing for

right and it it also has to do with

American values it's not just a sort of

commercial race so we can edge out uh

our nearpeer competitor both in the

public sector and the private sector

we're trying to win a race so that

American values prevail

uh inter internationally. Um Mr. Smith,

I want to move on to another topic.

Um it seems to me that on the consumer

side that one of the most

basic rights of a user on the internet

is to understand what they're looking at

or listening to and whether or not it

was created solely by a person, a person

using an AI or automatically generated

using AI. Do you think a labeling

regime, not a prohibition on the use of

AI, but just a disclosure uh especially

as it relates to images, music,

creativity, do you think a label would

be helpful for consumers? Uh generally

yes and I think that's what we in the

industry have been working to create. I

think you're right to make the

distinction and focus especially on say

images, video, audio files. Um there's a

standard called C2PA that we and a

number of companies now have been

advancing. Uh it has content

credentials. It enables people to know

where something was created, who created

it. And I think you're right to know

whether it was created by a person by AI

or a person with the help of say AI. Um

I just want to use sort of common

language, not the language that all of

you use or that we've all learned to

use. When you talk about the data as one

of the three elements that makes a model

work, data really is intellectual

property. It is human innovation, human

creativity. And I'm I I do think we we

may have a disagreement and I agree with

Senator Clolobashar about the need to

understand that these models have been

trained on data, but what we're really

talking about is human achievement all

the way up to now. And I I have a deep

worry. Look, I'm actually an optimist in

the energy space and the public service

space. Um, certainly in in health

innovation. There are a lot of really

exciting opportunities here. But we got

to pay people for their knowledge. And I

am concerned that these models are going

to be so successful in spitting out what

appears to be knowledge that we're gonna

on the back end not pay people for all

of the the inputs and we will have a

sort of stalling out of these models.

And and you talked about attention, but

I'm trying to figure out what the

tension really is other than you'd like

to pay as little as possible for these

inputs. Go ahead, Mr. Smith.

Um, well, I I I you had me until the

last sentence. I know. Hey, look, we're

we created intellectual property. We

respect intellectual property. So, we're

emphatically of the view that

intellectual property and the creation

of it should be rewarded. Ultimately,

intellectual property laws are always

about drawing the line. It's really the

line that you referred to. In copyright,

there is expression that is protected.

If you write a book and somebody copies

it, then you are entitled to be paid.

But there are ideas. If someone reads

your book, if someone remembers that,

you know, Shakespeare wrote a story

about two teenagers who fell in love,

sure, then that's fair. Then then that

that's fair use. That's that's why this

country created it. That's what we need

to focus on. With your permission,

chairman, I want to ask one final

question.

Proceed. Thank you.

Um, I'm actually quite excited about the

prospect that in 20 years people are

going to say, "Remember when you had to

wait on the phone uh to talk to Kaiser

Permanente or the VA?" So, I I just

maybe Mr. Alman and Mr. Smith, I want

you to, you know, a buddy of mine used

to say, "Paint a picture and paint me in

it." Okay? for for the government

actually delivering services. I want you

to describe what an AI agent or AI can

do to kind of reduce those pain points

that we accept as a fact of life in

interacting with the government. It

seems to me so much of what makes us

irritated with the government is the

lack of sorting data that exists

somewhere but we can't get access to it.

So just very quickly uh you have 15

seconds each for some cheerleading. I

can imagine a future where the US

government offers a uh AI powered

service that makes it really easy to use

all government services to get great

healthcare to get great education. You

have this thing in your pocket and if

you have any medical problem you get an

answer. If you need to, you know, like

appeal something on some process you're

having the government or file your taxes

or whatever. You just do it instantly.

You have an agent in your uh pocket

fully integrated with the United States

government and life is easy. Anything to

add? Remember when Remember when you had

to stand in line to renew your driver's

license? Remember when you didn't know

how to report a pothole that needed to

be repaired on your street? Remember

when you had a fender bender in a car

and you had to fill out all these forms

and talk to all these people to get

insurance coverage? Now you can do it

all with one AI system. You can use your

phone. And by the way, you can do this

today in Abu Dhabi. We need to bring it

to America. Thank you,

Senator Bud. Thank you, Chairman. Again,

thank you all for being here. I've

enjoyed uh various conversations with

each of you. The ability for the US to

deploy new energy generation capacity

and upgrade its grid, it's many ways the

key to the race against China. Energy is

how we can win and it's also how we can

lose. Permitting in this country, it

takes too long. China's command and

control system means that they will not

fail to deploy the energy needed to

achieve the scale necessary to develop

the most advanced models which will

drive all to the benefit of AI. So I'm

glad to be working with Senator Lumis on

the free act which would set up a permit

by rule structure which would let large

projects meet comprehensive standards at

the front end instead of dragged out on

a case-bycase process. So we all want to

protect the environment and we all want

to maintain US economic and

technological

leadership. So Mr. Entrator, uh what has

Cororeweave's experience been in

contracting power and are you concerned

that the current permitting system could

make it hard for the US to achieve

capital investment and the scale needed

to win this AI race?

So, as you said, um access to to power,

access to scale power, um is certainly

one of the keys to our ability to win

this race. There are there are others,

but it is uh uh one that I spent a lot

of time thinking about. Um the uh I

separated the comment into p access to

power and access to scale power because

I I do think that we are moving towards

a uh uh a period of this race where the

size the magnitude of uh the

infrastructure that is being required to

move um our artificial intelligence the

labs that are building it the companies

that are building it forward uh at the

velocity that's necessary.

uh is going to be a specific challenge

that that really requires a lot of

thought. We we have a huge part of our

organization focused on not just getting

access to power, but getting access to

the size and scale of power that's going

to be able to build the infrastructure,

you know, at the scale of Abalene or or

or close to it in order to um you know,

allow this to move forward. It's tough,

right? And it will get harder uh as we

move through time because the existing

um uh infrastructure that does have uh

opportunities. It has some level of

elasticity is going to be consumed and

once that is consumed, you're going to

get down to kind of a first principle.

How do we get power uh online now? And

that's really going to be challenging

within the regulatory environment as it

currently is configured. Thank you, Mr.

Smith. A similar question. How is

Microsoft trying to secure power for its

data centers? I mean, we read about that

in the news recently, but what does

federal policy need to focus on to make

sure that we don't lose this race

because we can't get enough energy? Um,

well, we invest to bring more

electricity generation onto the grid and

then to bring it through the grid to our

data centers. Um, we probably have more

permitting applications in more

countries than quite possibly any

company on the planet. Last time I

looked at it, it was 872 applications in

more than 40 countries. The number one

challenge in the United States when it

comes to permitting, interestingly

enough, is not local, it's not state, it

is the federal wetlands permit that is

administered by the Army Corps of

Engineers. We can typically get our

local and state permits done in about 6

to nine months. The national the

wetlands permit is taking off in 18 to

24 months. Both the outgoing Biden

administration and the incoming Trump

administration have focused on this. But

if we could just solve that, we could

accelerate a lot here in this country.

Very helpful. Thank you, Mr. Alman. Much

has been made about the Chinese open

source models like deepseek. Uh we spoke

about that a month or two ago. Uh a

concern that I have is that accessible

Chinese models promoted by the Chinese

Communist Party might be an attractive

option for AI application developers to

build on top of uh particularly in

developing world economies. So how

important is US leadership in either

open open source or closed AI models?

I think it's quite important to lead in

both. Uh we realize

that we open AI can do more to help

here. So, we're going to release an

open-source model that we believe will

be the leading model this summer uh

because we want people to build on the

US stack. In terms of closed source

models, a lot of the world uses our

technology and the technology of our

colleagues. We think we're in good shape

there.

So, how could federal policy further

help encourage AI ecosystem to be

developed right here in the US? Well,

you touched on a great point with

energy. Uh I think it's hard to

overstate how important energy is to the

future here. the you know eventually

chips network gear that will be made by

robots and we'll make that very

efficient and we'll make that cheaper

and cheaper but an electron is an

electron eventually the cost of

intelligence the cost of AI will

converge to the cost of energy and the

and if it'll be how much you can have

the abundance of it will be limited by

the abundance of energy uh so in terms

of long-term strategic investments for

the US to make I can't think of anything

more important than energy uh you know

chips and all the other infrastructure

also But but energy is where this I

think this ends up. Thank you, Chairman.

Um, Senator Kim.

Yeah, thank you.

Um, Mr. Smith, I think I think I'd like

to start with you because I I thought

your point about like what exactly is

the race, right? You keep talking about

the race and and you framed it in a

particular way saying that it's about

adoption in the rest of the world, the

78%.

I I guess I just wanted to ask you to

tease that out some more in terms of

understanding what role we could play in

Congress, in government in terms of

trying to accelerate and champion that

AI adoption internationally.

I think there's two things. The first is

it just shines light on the importance

of getting it right for export controls.

Yeah. Which is the AI diffusion rule

that's being discussed right now. And I

think what it shows is we want to have I

believe as a country the kinds of

national security controls that ensure

that say chips don't get diverted to

China or get accessed by the wrong users

say in China for the wrong reasons and

that is something that people have

drafted at the same in in in the

department of commerce. At the same

time, we need, I believe, to say get rid

of the quantitative caps that were

created for all of these tier 2

countries because what they did was send

a message to 120 nations that they

couldn't necessarily count on us to

provide the AI they want and need. And

just think about it. I mean, if this is

a critical part of your country's

infrastructure, how can you make a bet

on suppliers if you're not confident

that they'll be able to fulfill your

needs? So, I think you in Congress and

the Senate can help the White House and

the Department of Commerce get this

right. Mr. Alman, I wanted your thoughts

on this. Is that the right framing of

the race? Is it about the adoption

internationally in terms of other

countries? I I guess I'm trying to think

through it like part of what you just

said in your previous response was that

we want other nations to be able to

build upon the US AI stack. Is that the

right framework? Is that what we're

thinking about? Or is it more about the

consumer? Is it more about getting the

rest of the world and the 78% of the

population to adopt AI applications that

are US or is it interrelated? I I think

it's heavily interrelated. To me, the

stack is, you know, from the the chips

at the bottom to the applications on the

top. We want the whole world on the US

stack. We want them to use US chips. We

want them to use services like CH. Does

does having other nations building on

the infrastructure component of the

stack. Does that more or less then

guarantee or at least have a high

likelihood that then the consumers in

that country will be using our products

and applications? Is that the sort of

theory of the case?

it probably does make it marginally more

likely, but I also think

the if someone's using a stack that we

don't trust to train models, like who

knows what it's going to do? Who knows

what sort of back doors would be

possible? Who knows what sort of, you

know, data corruption issues could be

possible. Um, I I think the AI stack is

a increasingly going to be a jointly

designed system from the chip all the

way up to the the end consumer product

and, you know, lots of stuff in between.

uh I think separating that won't work

that well in practice and we shouldn't

want to like again I think this point

this is a very critical point that the

the leverage and the power the US gets

from having iPhones be the mobile device

people most want and uh you know Google

being the search engine that people most

want around the world is huge. We talk

maybe less about how much people want to

use uh chips and other infrastructure

developed here but I think it's no less

important and we should aim to have the

entire US stack be adopted by as much of

the world as possible. Yeah. I mean when

we are looking at you you're talking

about our investment into models uh and

building of that nature. How are we

doing in terms of development of the

applications AI tools and applications

though that are trying to embed in

people's lives? you know, not

necessarily just the overarching models,

but do you feel like we're putting the

level of intensity that we need to in

that in terms of that type of

development? Chat GPT is the most

adopted AI service in the world uh not

just in the United States, but in the

world uh by by a quite significant

margin. We're very proud that people

like it. Um and we we need to keep

pushing on that. I think it's important

for all the reasons you just discussed.

There are many other US companies

building incredible products and

services that are also getting globally

adopted. um this is what the US does

best. You know, Dr. Sue, I want to just

ask one last point to you. You know,

over and over again, each of you is

talking about talent as this incredible

power, but also could be a bottleneck to

us. How are we doing when it comes to

development of talent in this country?

If you were to give us a grade, what

would you grade us at in terms of our

development right now?

Thank you, Senator, for the question.

Look, I think the smartest engineers are

in the United States. We have a a great

base of talent but what I will say is uh

we need more we need more hardware

developers software developers

applications how wide is that delta if

we're talking about this as a race as

you did you know is that a space where

we have a larger amount of delta or is

that a place where it's it's closing

rapidly too well I I think we do have um

a very talented uh you know overall

talent base but we also have the desire

to have the best and that includes

includes not only you know US um

nationals but also having the the best

um you know international students

drawing the talent from that that's

right I think high-skilled immigration

is one of those areas where we want the

best people in the world uh to be uh

doing their work in the United States

and Senator if I can just add something

to your previous uh point about the um

the the cycle and and what race we're

trying to win. You know technology is

one of those things where you can have a

very vicious positive cycle. So in other

words, um when we lead and more people

adopt, that means uh more developers

that make our technology better, that

increases our lead. So that's what we

want is to have our leadership just

increase over time. Senator Schmidt,

thank you, Mr. Chairman. Uh Mr. Alman,

I'll start with you. I I uh really

enjoyed and was inspired by your story

with a light on um and the home you grew

up in in St. Louis, and you talked about

the spirit of innovation. That is the

spirit of St. Louis. As a fellow St.

Louis native. Um, that's a good story to

hear. And, uh, we just look forward to

more investment in St. Louis, uh, from

your company. That'd be great, too. Um,

so I'll put a plug in for that. Um, but

I do want to ask you, um, specifically,

there's a lot made of sort of the the

comparison between the United States and

the regulatory environment and what

exists in Europe. What specifically, and

I'll open this up to you, what

specifically has gone wrong in Europe

that we can draw um some conclusions

from? Uh first of all, we'd love to

figure out how to invest more in St.

Louis. I'd love an excuse to get to go

home more often.

Um I'll point out one example that I

think is just very

uh painful to users. When we launch a

new feature or a major new model, we

have what is now considered a little bit

of like a an in joke where we say we

have this great new thing not available

in the EU and a handful of other

countries because they have this long

process uh before a model can go out

and there will be I believe great models

and services that are quite safe and

robust that we will be unable to offer

in other regulatory regimes.

And if you are trying to be competitive

in this new world and if you are

consistently some number of months

behind what other people in other

countries get access to. Um that's

that's an example that's extremely

painful to users. And and you mentioned

um sort of your observation that the the

AI stack may may get more vertically

integrated. Um so how does that work

then? Because right now the best

estimates I suppose right is that I

don't know with China's two months to

six months behind maybe on on large

language models hopefully some of the

advances we're seeing in the US maybe

there's a degree of separation it's hard

to know exactly right with deepseek but

then you get down to the chips and and

that advantage is more like a couple of

years probably something like that so if

that's where we're headed does that

increase the US's advantage in your view

or does that sort of allow China to

catch up quicker as we get more

vertically integrated.

Um I I think there's a lot of things

that can increase US leadership, but but

we touched on this earlier. I think it's

so important. Uh there will be great

ships made around the world. There will

be great models trained around the

world. If the United States companies

can win on products and the sort of all

of the positive feedback loops that come

from how you can improve this once you

know real users are using your products

in their daily lives for their hardest

tasks. Uh that is something special that

is not so easy to catch up with just by

doing good chips and good models. So

making sure that the US can win at the

product level here obviously I'm like

talking my book a little bit but I

really do believe it is is quite

important. uh and that that's in

addition to all of the chips algorithm

the infrastructure algorithms and data I

think this is a new area where the US is

really winning and has a very strong

compounding effect. Thanks Mr. Intraor.

Did I pronounce that correctly by the

way? Yep. Okay. Thank you. Um I want to

turn a little bit sort of staying on

this this regulatory uh environment. One

of the things I think that's most

concerning that's coming out of Europe

is this sort of censorship regime um

that exists uh not just online but um in

real life um but certainly it's

happening online. I mean, people are

being arrested for things that they say

online. And one of the concerns I have

um um with AI I suppose is that if if um

we end up with a place where it's

somehow

policing quote unquote misinformation

and you know I think even in N's

uh most recent voluntary standards

um one of the risks to be on the lookout

for was the spread of misinformation.

Um, so the point of the question

is how do we make sure that I think part

of what's going wrong in Europe is it's

it's a sort of a um it's a funneling of

information and in my view whether I

agree with the point of view or not it

ought to be out there. People can make

their own decisions. You combat speech

you don't agree with not by censoring it

but by with with more speech. Um what

are some lessons to be learned there and

make sure that does not happen here.

So um Europe is moving forward with its

regulatory regime in a European way and

um from from our seat where we have to

make these enormous capital investments.

One of the things about the approach

that Europe is taking that we are deeply

concerned about every day is the uh uh

bulcanization to use to use um

um of how they go about uh um allowing

information to flow and how they go

about regulating and how they go about

uh um with each component of their uh

union having its own set of rules which

will be tremendously challenging uh in

Europe as time goes on um because it is

really hard to make the magnitude of

investments that we beyond beyond that

though jurisdictionally uh I'm talking

about content now. Yeah. So, so we're

we're not you our the role of our

company is really kind of below that.

Yeah. Um you know and and and uh um you

know uh um Sam and and and and you know

Microsoft you're going to get a lot more

attention paid to the content level

because of the role that they play in

the stack. It's not really where we are

primarily focused. We're really focused

on the investment side of it.

Yeah. If any of you would like to Sam if

you or Mr. Alman, if you would like to

respond to that, I'd like to get some

answer.

I I think well, first of all, I strongly

agree that people getting, you know,

like put in jail for stuff they say

online is is very not American, not what

we should be doing. The the AI is quite

different than social media, at least in

its current evolution. Um, people are

using these tools in this sort of

one-on-one way instead of this

massive thing online. So, I I think it's

it's easy to make too many analogies uh

but it's a little bit dangerous to try

to talk about AI and the things we're

going to face here in the same way

um that we did for social media. But,

but our stance is that we need to give

adult users a lot of freedom to use AI

um in the way that they want to use it

and to trust them to be responsible with

the tool. And I I know there's

increasing pressure in other places

around the world and some in the US to

not do that. But uh I think this this is

like this is a tool and we need to make

it a powerful and capable tool. We will

of course put some guardrails in very

wide bounds. But um I think we need to

give a lot of freedom. Yeah. I'm out of

time, but there's a lot more questions

there that we'll follow up with. Thank

you, Miss M. Madam Chair. Thank you,

Senator Hickin Looper. I appreciate that

line of questioning. I was I was ready

for you to continue as well. I could

have given you a minute or two. Um, Mr.

Smith, uh, Microsoft has a long and deep

history in transforming workplaces all

over the world through software, uh,

from Windows operating system to its,

uh, office applications like, uh,

PowerPoint, uh, Excel, uh, and now the

AI powered co-pilot application. Um, in

software development, life cycles seem

to be becoming increasingly shorter,

updates becoming more frequent. um what

are the internal processes that

Microsoft follows to evaluate C-pilot's

accuracy and performance before it was

released and what kind of independent

review teams other than Microsoft's own

product developers are involved in that?

How who do you bring in to help with

that? Um well, first of all, since most

of what we're talking about here when

you're talking about uh our co-pilots

start with models that are developed at

at OpenAI, I would say OpenAI has its

internal process. There is then a joint

what's called a DSB, a deployment safety

board where we decide together whether

something is safe to deploy. As the name

implies, we then at the applications

level have our own internal deployment

safety board. Uh we have a variety of

engineering tools that we use to assess

these features. We test these features.

We have red teams meaning sort of

competing teams that often go to work to

sort of attack the features and then

ultimately the product is released when

those tests are completed and the

results are satisfactory.

Good. I like that. Um well, let me go

over to Mr. Alman. The obviously you all

have a natural incentive to ensure that

the products are high quality and safe

and uh but the field is so competitive

and

um you know in applied research

uh and with rigorous testing um these

constant improvements really are

fundamental steps to the performance of

a model. So risk risk assessments are uh

that key tool. Um and I'm a big believer

in in evidence-based technical

standards. Uh I've been accused of being

the only real scientist who's published

peer-reviewed papers in the in the

Senate. Um so Mr. man. Uh do you believe

that under appropriate circumstances uh

independent evaluations based on uh

standards performed by qualified out

evaluators

uh and done voluntarily could help

validate the testing that you're perform

performing internally and in conjunction

with uh peer companies. Thank you

Senator and I think it's awesome that

you are have published peerreview papers

and would love to see more of that. Well

listen I was on the Maslov's triangle of

science. I was near the bottom. I was a

geologist. So that's, you know, not high

up in that. Geology is great.

Um, yes, I think what you say is very

important. It's an important part of our

process today. Uh, external testing

helps us find things that we may have

missed internally. And as we're we're

very proud of our safety record on the

whole. Not that we you know we've not

been perfect and we're continuing to

learn new things, but I think we do have

a process that is leading towards models

that the public generally thinks are

safe and robust to use. Um and we've

developed a lot of techniques to be able

to continue to deliver that. But

external testers and redteamers uh are a

critical part of that process and I

think they've helped us find many things

in the models to improve. And M. Smith,

would you add anything to that? No.

Okay. Got it. Someone giving testimony

who doesn't have something to add.

That's a moment of scientific

reflection. Uh Dr. Sue, the bipartisan

chips and science act, uh historic

effort to try and maintain US leadership

in emerging technologies like

semiconductors, but others as well. U as

the technology arms race continues

globally and you were talking about

this. Uh AMD plays a key role in

delivering um state-of-the-art designs,

the the best u for the new chips that

are going to power electronics and the

devices that are going to allow AI to

become global. um as scientists work

around the clock to develop new

breakthroughs um and to try

and increase and improve performance but

at the same time shorten R&D timelines.

Um what do you see as the next frontier

of chip technology in terms of of energy

efficiency? uh and how can and that's

not just based on on the Chinese

competitors but how can we work together

to improve uh direct to chip cooling for

high performance computing well uh thank

you for the question senator I would say

look there is a tremendous amount of

innovation that's going on in the

semiconductor sector today uh the chips

and science act was certainly helpful in

raising the profile of chips in the

United States uh relative to you know

what are we doing to uh go faster and

build uh better and more power efficient

chips. Uh frankly, we're using AI um

extensively through our chip development

um cycles. And it it it does allow us to

augment what are you typically very long

cycles, many years um you know several

years for us to develop chips. We can

shorten the time and also uh improve the

efficiency. And there are lots and lots

of great new technologies in terms of

cooling technologies that are super

important for us to build the

large-scale systems that we talked about

earlier today. So, thank you for the

question. You bet. All right. I'm out of

time. I'll yield back to the chair.

Thank you all. And and Senator Hickin

Looper, I will say as a Texan whose

parents were in the oil and gas

business, I think geologists are

awesome.

We have a consensus.

Uh Senator Curtis, thank you, Mr.

Chairman. Uh, it's delight to be here.

Mr. Alman, I I um you started kind of a

oneupmanship on computers and I will

just tell you in 1985, the month you

were born, I was attending a class at

Brigham Young University and carried in

a laptop and was almost kicked out. What

laptop? It was a TRS80. Oh, awesome.

Made by Radio Shack. I upgraded the

memory from 40K to 80K. Ran on on four

AA batteries and uh That's incredible.

Yeah. So I'm very envious of your

generation. Let let me start with you if

I would. Uh I think you know Utah would

aspire to lead out with data centers and

and advanced technologies. Could you

just address for states and in Utah

specifically what it is that makes them

attractives to projects like Stargate?

Yeah, and I know that we're uh having

productive discussions about some

potential sites in in Utah. um power,

cooling, fast permitting process, labor

force that can build these things, the

electricians, the construction workers,

the entire stack. Um a state that wants

to like partner with us to to move

quickly. Texas really has been

unbelievable on this. Uh I think that

would be a good thing for other states

to study, but we'd be excited to try to

fix something out. Thank you. I think I

can speak for our state state leaders.

We would be excited as well. But as you

know, this also brings challenges and

one of those challenges are the demands

for energy and um what's your thoughts

on how we protect rateayers and and kind

of put a little bit of a firewall

between

them? I mean I think the best way is

just much more supply more generation.

Uh you know like I think if if you make

it easy to reasonably profitably create

a lot of additional generative capacity

the market will do that. uh that will

not only not drive up rates because of

the AI workload, hopefully it'll drive

it down for everything. And we've talked

a lot about the importance of energy to

AI. Energy is just really important to

quality of life. Uh one of the things

that seems to me the most consistent

throughout history is every time the the

cost of energy falls, the quality of

life goes up. And so doing a lot to make

energy cheaper. Um in the short term, I

think this probably looks like more

natural gas. Um although there are some

applications where I think solar can

really help in the medium-term I hope

it's advanced nuclear uh fish and fusion

more energy is important well beyond AI

um you know in some sense we have these

dual revolutions going of AI and energy

the the ability to have new ideas u and

the ability to get them done to make

them happen in the physical world where

we all live like these are kind of the

the limiting reagents of prosperity and

let's have a lot more. Thank you. Um Mr.

Smith. Uh we've talked about how

significant power was is uh to the

success here. Uh what role do you think

Microsoft and other tech leaders have in

developing energy and particularly the

right type of energy? Um I I think we

have a tremendous responsibility to

contribute to the solution and I think

Sam helped uh with his list. I would

highlight two things and I just would I

guess illustrate it uh with what we do

everywhere but most recently um with a

major site in southeastern Wisconsin.

You know we went from zero basically to

becoming the largest industrial user of

electricity in the state roughly 400

megawws and you know so we worked with

the local utility we made the investment

to ex help and really enable them to

expand their electricity generation. Now

that electricity then needed to be

delivered from their power plant through

the grid to our data center. Um we went

to the public utilities commission and

we proposed a rate increase on

ourselves because we thought it was

important that we pay for that

improvement to the grid so that the

neighbors so to speak would not have to.

And I think what it really illustrates

is the collaborative partnerships that

are needed to provide the capital to do

the construction to improve the grid and

to be I think very sensitive to the

community as a whole. Thank you. Uh Mr.

Altman, let me come back to you. I I was

a small business owner. I have a special

spot in my heart for small business

owners. Can we talk a little bit about

uh chat GPT and um how that might assist

small business owners and and let me

paint a little broader picture. We've

heard a lot about other tools that are

perhaps out of favor uh particularly

with the US government that are very

helpful for small businesses, but I

don't know if if small businesses are

fully understanding the platform that

you have and how they might use it for

marketing, for data research and and

ways to help their small business be

successful. one of you there were all

these moments as Chachib was beginning

to take off where we would be like oh we

may have like a hit on our hands there's

like that's someone's using it for this

and this and that's you know strangers

talking about it you see someone using

it in a coffee shop but one of the ones

that really sticks out for me is pretty

quickly after chatbt launched um like in

the first six months say um I was in an

Uber um and the driver was making

conversation he's like have you heard of

this thing called Chacht it's amazing

and I was like yeah like what do you

think about and he was using it to uh

run basically his entire small business.

He was like I had he ran a laundromat

and he's like I had all these problems,

you know, like couldn't find good people

to write my ads, couldn't get like legal

documents reviewed, couldn't like answer

customer support emails. And he was like

a mega early adopter, but he was one of

these people that was using AI to like

make a small business work. And that was

we talked about that story a lot at the

time. Um but I was it's nice to reflect

on it again now. We've now heard that at

scale from a lot of people, but that was

one of those moments early on we're

like, "Oh, this is maybe gonna work."

So, and I'm out of time, but just Mark,

this is more than just something that

helps proofreads emails. Um, right. And

and you don't need to comment because

I'm out of time, but we'll I think we

would all agree with that. It is and and

look forward to seeing these

applications move forward. Mr. Chairman,

I yield my time. Senator Duckworth.

Thank you, Mr. Chairman. I thank you for

the panel for all of you being here

today. I want to begin by talking about

the importance of partnerships between

the private sector and our national

laboratories in maintaining United

States leadership in AI. Illinois is a

proud home of two crown jewels of the

national laboratories. Firmenilab,

America's premier particle physics and

accelerator laboratory and Argon

National Laboratory, home to the Aurora

Supercomputer that will accelerate

breakthroughs in AI, cancer research,

and fundamental physics. There is

nothing more important than sustaining

and amplifying investments in our

nation's incredible network of national

labs. Yet, Donald Trump and Elon Musk,

with the support of some Republicans in

Congress, applauding to take a chainsaw

to the vital research initiatives being

carried out across our country. This is

a self-sabotaging attack, plain and

simple. Um, and if allowed to proceed,

Trump and Musk will inflict lasting harm

on our innovative capabilities and

capacity that our enemies could only

dream of achieving. Does anyone truly

have confidence that had Doge been

around decades ago, they would not have

cut the project that created the

internet as an example of wasteful

publicly funded research and

development? So my question to any

member of the panel is the following.

Can you explain the importance of the

national lab system to maintaining our

research edge and discuss any

partnerships you've established or are

currently pursuing, especially those

threatened by massive cuts to the

national labs research?

We partner with the national labs. So

maybe I could take a first of this.

Uh also, Senator, I would love to get to

visit a firm lab someday. That would be

like that was my next question. That

would be a real life. That'd be very

cool.

Um there's many wonderful things that AI

is going to do for the world. Uh but the

one that I am personally most excited

about is the impact AI will have on

scientific discovery. I believe that new

scientific discovery is the most

important input to the world getting

better and people's quality of lives

getting better um over time. it is uh it

is hard to overstate where we would be

um if where we are because of scientific

advancement and where we we would be

without it. So, we're thrilled to get to

partner with the national labs on this.

Um I think science has not been as

efficient as it can be and we're we're

also thrilled to hear from scientists

that they're, you know, multiples more

effective than they used to be. And I

think that AI tools will mean we can

accomplish at some point a decade worth

of scientific progress in a year for the

same cost or even less. Um this this

will be one of the most important

contributions in my opinion that AI

makes to the world. And um it's no

longer theoretical like the national

labs are are a great example. That's the

only partnership where we've given a

copy of our model weights to another

organization. Uh it's a very deep and

important partnership to us and I expect

that that will really bear fruit. Thank

you. Anybody else on the panel? Doc.

Yeah, I I think

you highlight a very important issue.

You know, this country has 17 national

labs administered by the Department of

Energy and about 85 to 90 research

universities. And you together they are

the fabric of much of scientific

discovery and have been since the

Manhattan project in World War II. Um,

we in the tech sector, we at Microsoft

work with most almost all of them. And

there's a particular cycle of innovation

that the United States has mastered. You

have curiositydriven research in these

institutions and then the advances move

out of those institutions into startups

and into larger companies. And what I

always find interesting is I meet with

officials around the world. They have

studied this. They seek to emulate it.

And I always worry that in the United

States, we run the risk of taking it for

granted. We should never take this for

granted. It is the foundation for the

country's technological leadership. Very

much so. Dr. Sue, I just wanted to add

to that. Uh we are also very large

supporters of the public private

partnerships with the national labs. I

think the national labs have um you know

in a way always tried to look ahead of

the curve and you know that's a great

place for us to invest. We think there

are a key piece we have partnered with

all of the national labs as well um you

know over the last decade and you know

that continues to be a place where I

think there can be significant public

private partnership. Thank you Mr.

Andre. I I just think it would be really

interesting to come

to these AI factories and to walk or

travel through these institutions or and

identify all the different pieces of the

science that leads back and was

ultimately driven and founded on

something that came out of those

institutions because I it's amazing

actually. Thank you. And would any of

the remain three of you would like to

come to a lab in Illinois either Fermy

or Argon? I will give you personal

tours. All right, all four of you. It's

done. Thank you, Mr. Chairman.

Thank you, Senator Young. Thank you, Mr.

Chairman, for uh holding this important

hearing on winning the AI race. It's

it's good to see our panelists here. One

of the things that um uh I like to

underscore whenever I talk about this

issue is uh we are not just discussing a

race to create jobs. uh not just

discussing uh a race to figure out how

to ek out more growth from our economy,

although that's important. Um not just

trying to identify how humans can

flourish more uh especially Americans

through uh application of AI solutions

to our daily lives in various ways. But

this is an issue of national and

economic security. I want folks at home

to get that. I know all our panelists

are are highly conversant and and and

knowledgeable about that.

Um, in my discussions with you and and

and many others, I' I've heard we need

to work with like-minded partners and

allies to uh to win this race. And it's

only going to be done collectively. I've

heard here today from a number of you

that um this race is in part about

getting market share diffusion of our AI

models and and solutions into other

countries. Uh it is through that means

for me to perhaps elaborate on your

thoughts uh that we can see that our own

values are advanced. uh these models

presumably they'll they'll be embedded

with our values related to privacy and

transparency and property rights and

freedom of speech and religion um the

not the values of the Chinese Communist

Party on each of those various fronts

and then if we can establish digital

trade rules digital crossber agreements

on on digital trade with these other

countries we could conceivably erect

higher barriers to entry for models that

don't uh come embedded with our

standards models of of say the Chinese

Communist Party has given sanction to um

so there's a

geopolitical national security overlay

to this entire conversation what which

is why I think the chairman's emphasis

on not overly constraining innovation uh

or deployment is very important but it's

also why I think it's important that we

be thinking about how to work with other

countries um in their standards

development. Um and so that's that's

where u I I want to begin asking

questions. I'll start with uh Mr. Smith.

If the United States doesn't adopt some

standards through some entity, whether

it's NIST or another federal entity or

federally sanctioned entity, then um

won't other nations go ahead and feel

the need to adopt their standards

without any consultation uh with the

United States? Uh I think it's a really

important point you make and it is the

lesson from the evolution of privacy

law.

The United States didn't adopt a

national privacy law. Europe did twice

and most American companies of any size

today apply across the United States

work that complies with European privacy

law. It's just more efficient. So I

think the United States needs to be in

the game internationally to influence

the rest of the world. And you cannot be

in the game if you do nothing. You must

do something. So you take Senator Cruz's

idea, a lightweight approach. Yes. And

then you build support around it. So

just to unpack that, and I'll stick with

Mr. Smith with apologies to everyone

else because my time's limited. Um would

it be easier to shape the standards of

other large economy countries that share

most of our values if we already have a

set of standards adopted?

Generally, yes. I think we always have

to be careful because if you go too

soon, you go before the standards have

really come together, but you've got to

have some kind of model that you can

show the rest of the world and win

support for. And then presumably

standards could be harmonized, right?

They're not set in and and chiseled onto

a a tablet, so to speak, right? No,

that's indispensable. I mean, if our

technology is going to go around the

world, we need a set of laws or

regulations that in effect create that

basis for reciprocity and

interoperability.

Okay. Um, I only have 25 seconds left.

Are there any violent objections uh to

Mr. Smith's uh position? Because that

that seems eminently reasonable to me.

Seems consistent with the light touch

approach, but it off also shows a

certain sense of urgency that the United

States needs to act. The last last thing

I'll say in my remaining 10 seconds is

that uh I am planning on introducing

legislation today called the AI public

awareness and education campaign act

with several of my colleagues. Uh and uh

our aim is is to have a whole of

government approach to foster greater

awareness of AI literacy and grow STEM

opportunities to create the next

generation uh of our workforce and um

looking forward to moving that forward.

So, uh, it will be available for, uh,

public review, critique, uh, even

accolades. And Mr. Chairman, I yield

back. Thank you, Senator Bent Rochester.

Thank you, Chairman Cruz, and thank you

so much to the witnesses. Um, this is

such an important hearing. Five minutes

will not suffice for me. I'll be

submitting some questions for the

record. Um, I noticed that for Mr. Alman

and, u, Mr. Smith, when the question of

paint me a picture of the future came

up, there was you actually leaned up in

your chair. There was a level of

excitement and that's how I am about the

future. Uh when I came into the House of

Representatives in 2017, I started a

future of work uh bipartisan caucus

because I had a concern that um number

one there were certain groups of people

that were going to be left behind, but

there also as a country that we could be

left behind. And I started I had one an

event where we had everyone walk into

the room and use a word cloud and tell

me what you think of when you hear the

future of work. The biggest word coming

in the door was fear. The biggest word

walking out the door was opportunity.

And so to me, this conversation is so

vital to think about the opportunities,

but also making sure that we are

watching out for ethics, watching out

for scams, watching out for that

technology does not take over the human.

And so I am just grateful for the

conversation and um Mr. Mr. Alman, I I

listened to a interview uh about uh that

you gave with Lester Halt maybe a year

or so ago and you talked in that

interview about um how open AAI it

wasn't initially even about making a

product. it wasn't about the money. And

so I know you are incorporated in

Delaware and I understand you've been

working with our attorney general um

during uh the previously proposed

legislation to transition to a

for-profit not legislation but to

transition to for-profit. And this

Monday um Open AAI decided to apply to

become a public benefit corporation

instead and to have the PBC govern your

nonprofit arm. um what went into this

decision and what considerations

influence the timing of the

organizational change?

So, we we never Thank you for the

question, Senator, and the chance to

explain this. It's a complicated thing

that I think has gotten misrepresented.

So, this is a wonderful forum to talk

about it. Um we never planned to have

the nonprofit convert into anything. The

nonprofit was always going to be the

nonprofit. Um and we also planned for a

PBC from the very beginning. There were

a bunch of other considerations about is

it the PBC board that would control the

nonprofit somehow or you know h how our

capital structure was going to work that

there was a lot of speculation on most

of it inaccurate in the press but our

plan has always been to have a robust

nonprofit. We hope our nonprofit will be

one of the best maybe someday the best

resourced nonprofit in the world and a

PBC with the same mission that

would make make it possible for us to

raise the capital needed to deliver

these tools and services at the quality

level and availability level that people

want to use them at but still stick to

our mission which we've been proud uh

over the last almost decade of our of

our progress towards. So, we had a lot

of productive conversations with a lot

of stakeholders and a lot of lawyers and

a lot of regulators about the best way

to do this. Um, it took longer than we

thought it was going to. Um, you know, I

would have guessed that, uh, we would

have been talking about this last year,

but now we have a a proposal that, uh,

people seem pretty excited about and

we're trying to now advance. And Dr.

Sue, um, your company primarily operates

in the physical hardware portion of the

AI stack. Um, I have a bill with

Senators Canwell and Blackburn called

the Promoting Resilient Supply Chains

Act, which authorizes the Department of

Commerce to strengthen American supply

chains for critical industries and

emerging technologies. Uh, Dr. Sue and

others um semiconductor and chips

manufacturing is critical to advancing

the advancement of AI, but we're facing

these global supply chain constraints.

What specific policies and I know um you

mentioned policies as well for a uh

supply chains would we need to adopt uh

to help American companies overcome uh

the supply chain issues and compete in

international with our rivals. Thank you

Senator for the question. Uh there's no

question the semiconductor supply chain

uh and overall supply chains are really

critical for us to win the AI race. Um I

think from a semiconductor standpoint

the efforts that have been made to move

uh manufacturing back to the United

States um have been positive. I think

they are start there's a lot more that

we can do and one of the most important

aspects of it is um really to think

about it end to end. There's so many

steps to go from beginning to end in a

um in a semiconductor supply chain

including advanced wafers, including

packaging, including the backends and

and system test. All of those a avenues

need to have a footprint in the United

States. And then we have many allies

around the world which are you know very

excellent partners as part of the global

resiliency in the supply chain and we

would like to see um you know those

partnerships continue to flourish. And

last question if I can um Mr. Smith, how

do you see the interdependence between

the AI stack sections creating either

vulnerabilities or opportunities in the

AI supply chain?

I think they create more opportunities

than vulnerabilities because it enables

companies to do what they do best and

then we can work together. And you know,

the world today has an integrated supply

chain for anything that you buy. We just

don't think about it. when we go to the

grocery store. Um I think one of the

strengths of the tech sector is that we

have I'll call it a string of pearls.

Great companies in very in every layer

of the stack and we're going to need

frankly more great companies especially

at the applications layer and that it is

how we work together. Thank you so much.

I am out of time but uh we will be

following up with questions for the

record as well as individually. Thank

you and I yield back.

Mr. Moran, Chairman Lemus, thank you

very much. Uh Mr. Smith, Mr. Smith

mentioned uh data privacy uh which has

been a topic of mine for a long time and

we've been unsuccessful in legislation

being adopted, but I still have the goal

of making certain that consumers have

control over their own data. And I was

going to ask you, Mr. Alman, how can we

provide consumers with more control over

how their data is used by AI companies

while preserving the utility of the AI

system? So, how do you get more privacy

and still get the

benefits? So, there's all of the

standard privacy controls that companies

like ours and others build and should,

but there's a new area that I'd love to

flag for your consideration, which

is people are sharing more information

with AI systems than I think they have

with previous generations of technology.

And the maximum utility of these systems

happens when the model can get very

personalized to you. Um, so this is a

wonderful thing and we should find a way

to enable it. But the the fact that

these AI systems will get to know you

over the course of your life so well, I

think presents a new challenge and level

of importance for how we think about

privacy in the world of AI. How we're

going to think about guaranteeing people

privacy when they talk to an AI system

about whatever's happened in their

lives. how we make sure that when one

system connects to another, it shares

the appropriate information and doesn't

share other information and that users

are in control of that. Um, I I believe

this will become one of the most

important issues with AI in the coming

years as people come to integrate this

technology more into their lives and I

think it is a great area for you all

to think about and take quite seriously.

Uh, we do we just don't have any success

in finding the conclusions but thank you

for the encouragement. Um I chair a

commerce justice science appropriation

subcommittee that funds the department

of justice and it plays a significant

role in um cyber security of our

country. Uh I just came home from a

budget hearing with the FBI director

director Patel in which we covered cyber

security threats. AI can you and I think

this is true. AI can be used on both

sides of a cyber security attack and it

can be used to automate automate

fishing, malware creation, but machine

learning can also increase our ability

to detect uh and respond to cyber

threats. Um what should Congress think

about allocation of federal resources

for cyber security and what should we

consider when it comes to AI?

Well, I would say that, you know, AI, as

you said, is both an offensive weapon

and a defensive shield when it comes to

cyber security. And as with many other

things, the front line of this the last

few years has been in Ukraine because

Russia has such a sophisticated cyber

attack capability. And you know what

we've found as a a company that's been

involved in supporting Ukraine since

literally the moment that war began is

that AI is a gamecher. Um you know we

have intercepted attacks against Ukraine

faster than a human could detect them

and we block those attacks from taking

place. So you deploy AI into call it the

front line of the products themselves.

Um we have to recognize that the it's

ultimately the people who defend not

just countries but companies and

governments the chief information

security officers or the sysos you know

so we've created what's called a cyber

security co-pilot that basically

automates for those individuals much of

the workflow that takes their time so

that they can be more effective and

efficient when it comes to federal

appropriation ations. I think that to

put it simply, the United States

government must remain at the forefront

of having for itself the cyber security

capabilities that it needs to defend the

government and every day. I mean, we are

in government agencies today during this

hearing, you know, pushing Chinese out

of agencies and the like. And this will

be happen every day of every year from

now to probably eternity. So we must

keep the US government well funded in

this space and I think we also need our

intelligence agencies and especially the

NSA to be well funded so they can remain

at the forefront when it comes to global

leadership in this field. Uh thank you

for your observations and and

encouragement. My final question, uh,

rural areas, a place I come from, um,

often lack high-speed

broadband. And since many AI tools rely

upon connectivity, I'm concerned that

many parts of the country and many parts

of Kansas may not be able to access the

benefits that AI will bring to business,

schools, health care, etc.

What can the federal government do to be

supportive of development and

availability of ondevice or low

broadband width uh AI systems that do

not rely on constant

connectivity. I'm generally pretty

excited about what AI will do here

because you can offload so much of the

processing to the cloud uh and then ship

a relatively small amount of data. If

you think about, you know, chatbt is

text comes in, there's like a brain that

thinks about it really hard and some

text comes back. We can support people

in low connectivity areas quite well

with the same quality of service. I

separately to that I think getting great

connectivity everywhere is important,

but in the specific area of AI, I think

we can actually address that uh address

that gap quite well. That's good to

know. Thank you very much,

Mr. Luhan. Thank you, Madam Chair. And

first I want to begin by recognizing and

thanking Mr. Altman and Mr. Smith for

your organization's ongoing involvement

in the NIST US AI Safety Institute as

well as Dr. Sue and Mr. Alman for your

ongoing partnerships with our national

laboratories. Now Dr. Sue, Mr. Alman,

can you explain how your partnership

with the national labs support

scientific research? You explained this

uh to a question that was asked by

Senator Duckworth as well, but if you

could just touch on that quickly.

Our latest models uh like 03 are good at

scientific reasoning. And so scientists

are able to use these to help them

review literature, come up with new

ideas, propose experiments, um analyze

data in a way that the previous

generations of models just couldn't.

We've had the national labs and other

scientists spend time with previous

models and they say, "Oh, this is, you

know, kind of cool. It's interesting.

not transforming thing the things these

these new models are the first time

we're hearing from scientists at the

national labs and elsewhere that this is

a legitimate gamecher to their research

output. Appreciate that Dr. S. Yeah, I

would add um the same. I think our

partnerships with the national labs have

seen just um you know tremendous

opportunity. uh we have large-scale

compute um across the national labs and

the ability to really develop new

applications that take advantage of

let's call it traditional high

performance computing together with the

new AI uh model capability that we just

talked about is I think a great

opportunity to substantially move

forward the ability for scientific

discovery to to both of you again can

you explain why federal investment in

foundational research and standards

bodies are crucial to your companies

I I think standards can help uh increase

the rate of innovation, but it's

important that the industry figure out

what they should be first. Uh I think a

bad standard can really set things back

and we've seen many examples of that in

history. I do think there's a new

protocol to discover here at the level

of importance of HTTP. This is just one

example. There's many other things too.

Um I believe the industry will figure

that out through some fits and starts

and and then I think officially adopting

that can be helpful. Dr. I believe uh

public private partnerships really

enable us to think let's call it ahead

of the curve. So there are lots of

things that we do in industry and we do

them very very well. Um however the the

beauty of the national labs and federal

research is it does allow let's call it

a bit more blue sky research and I think

that's a very you know positive ad. So I

think the key is how we can make sure

that you know one federal dollar goes

much much further than that with a a

private investment on top of that.

Yesterday I reintroduced a piece of

legislation called the Test AI Act which

has bipartisan support which would

simply improve the federal government's

capacity to test and evaluate in this

area as well. Uh so very much appreciate

both your responses. Um, but this is

just one of many steps I would argue

that is needed to uh ensure that the

United States stays ahead. Now, despite

strong support across the country,

including from industry leaders here

today, President Trump's annihilating

budgets for basic research, and there

are questions abound by so many. I'll

argue that this will destroy our

nation's competitive advantage. Um, I

simply just call on all my colleagues

that we look at the investments to the

National Science Foundation, National

Institutes of Health, and Department of

Energy, Office of Science. Let's work

together. If there's questions that we

have, let's find ways to address those,

but let's ensure that these investments

are making a positive difference so that

we have more successes and more hearings

celebrating what we're celebrating

today. Now, beyond your partnership with

the federal government, I would like to

know more about how you partner with

local communities when building out

centers. Um, data centers put a strain

on energy and water resources. However,

unlike other businesses, they do not

introduce many long-term jobs and

economic benefits necessarily. So, Mr.

Smith, how many engineers do you have

dedicated to model or hardware

optimization to reduce energy use? And

when you build a center, what

initiatives do you have in place to

reduce water use?

Um I don't know off the top of my head

the number of engineers working on

optimization but be happy to track down

an answer and get it to you. Um water

use is a huge priority especially uh you

know in data centers for example in the

southwestern United States and other

countries around the world where water

is in short supply. If you look at our

data centers today um they run on liquid

cooling. Uh it's a closed loop system.

The uh liquid is a combination of

frankly water and other chemicals. But

basically once it starts running almost

all of the water is recycled. So the

amount of water that we consume is

typically far far smaller than what most

people would estimate. We also have a

commitment to water replenishment. Our

our goal is to be water positive meaning

that we're providing more water to the

community than we are consuming. So, for

example, across the United States today,

we have more than 90 water replenishment

projects, including one that focuses on

the San Juan River in in in your state

of New Mexico, which focuses on water

security for the the river. So, I think

it's a good example of how we can play a

responsible role in addressing an issue

that is of growing importance.

Appreciate Mr. Trader, same question.

Yeah, I I would I can't answer the the

question of how many engineers we have

focused on it, but I I will say that the

the ability to extract more

computational power out of a given

megawatt is

of paramount importance uh to my company

to to the to to to all of us in this

room. And um we spend uh an enormous

amount of time uh integrating the the

most bleeding edge technology which is a

step function more efficient in terms of

its computational output than uh the the

legacy uh uh technology uh has

historically done. Um you know so moving

to liquid cooling has just been an

incredible uh improvement in efficiency

and ultimately we we we face this

problem from you know within a given uh

data center within a given uh uh power

envelope how much can we move uh the

computational resources forward and

that's really an important part of what

we do. I appreciate Mr. Chairman I have

other questions I'll submit to the

record. Mr. Moran did ask one question.

Mr. Shman, you responded to it, but can

you all just answer yes or no? Is it

important to ensure that in order for AI

to reach its full promise that people

across the country should be able to

connect to fast, affordable internet?

Dr. Sue.

Yes. Yes. Yes. Thank you. Appreciate. I

yield back. Thank you. Thank you,

Senator Lumis. Thank you, Mr. Chairman.

Uh, and thank you all for coming today.

I really have been amazed at the

outstanding progress that continues to

be made in this field. And I'm already

seeing people in Wyoming that are using

Chat GPT or Claude to improve their

businesses, whether it's healthcare or

mining or oil and gas or education,

uh ranching even. Uh I'm just really

excited about what this opportunity

brings to America. Now, as I see it, um

the world has presented us with two

paths. On one hand, the EU has chosen to

regulate first and ask questions later.

The GDPR is already limiting European

access to the most capable AI models. On

the other hand, China appears to be

fasttracking AI development, standing up

large amounts of energy very quickly in

an attempt to outco compete America. So

I'd like to ask a few questions about

how we can make sure we get the full

benefit of this technology and

accelerate its development. So first

question

uh over the past year we've seen many

states including California and Texas

consider their own AI frameworks each

one significantly burdensome in their

own right. At the same time, our lead

against China is shrinking to about only

six months. Um, so first of all, Mr.

Altman, could you please sketch out what

the world could look like if the US were

to have a patchwork regulatory framework

and how that could impact our

competitiveness?

I I think it would be quite bad. Uh I

think

it it's very difficult to imagine us

figuring out how to comply with 50

different sets of regulation. Uh and in

many of these states there have been you

know dozens of different bills proposed

that I understand several of which could

could be passed. Um that will slow us

down at a time where I don't think it's

in anyone's interest for us to slow

down. uh one federal framework that is

light touch uh that we can understand

and that lets us you know move with the

speed that this moment calls for seems

important and and fine. But the sort of

every state takes a different approach

here uh I think would be quite

burdensome and uh significantly impair

our ability to do what we need to do and

hopefully you all want us to do too.

Does anyone disagree with Mr. Alman's

assessment of a patchwork?

Thank you. Um I have some questions

about the infrastructure

uh that is going to be necessary to uh

lead and compete in AI. So my next

questions are for our infrastructure

providers Mr. Smith and Mr. is it in

trader or in that's correct in trader.

Thank you. Um could you elaborate on how

current permitting processes have

impacted your ability to rapidly deploy

AI infrastructure? the more specific you

can be, the better.

So, um, uh, quick comment on the

patchwork, uh, and then I'll, I'll dive

in here is, um, the investment that

we're making on the infrastructure side

is enormous. And the idea that you can

make an investment that could then

become uh uh trapped in a jurisdiction

that has a particular type of regulation

that would not allow you to make full

use of it is uh um really very very

suboptimal um and and makes the decision

making around uh infrastructure

challenging. Um as as far as the the the

permitting goes

um whenever this topic comes up the the

discussion um around permitting is

excruciating and it's excruciating from

the ability to quickly build and to

build large and I think that is kind of

from the data center forward without

even beginning the discussion from the

data center back through the energy

infrastructure that is necessary.

neessary to be able to power these large

investments at the scale that make them

of relevance to moving uh artificial

intelligence forward. Um happy to spend

more time kind of digging into more

details, but but but uh um probably do

that directly. Okay. And I'll look

forward to that conversation because I'm

worried about Wyoming's very clean

natural gas

uh being um something your industry is

concerned about because uh President

Trump likes natural gas, but President

Biden didn't. And if you build huge data

centers and another president comes

along who's anti-natural gas,

um that's a concern for you as you're

deciding how to deploy capital. Mr.

Smith, do you agree? Uh, generally I do.

I mean, I would would say we need

consistency across administrations in

this country. Uh, we need to find more

opportunities for bipartisan agreement.

Um, and I'll just highlight that in

Cheyenne, where we've long had a data

center complex. Um, you know, we do have

backup generators that, you know, run on

natural gas. So you there are a variety

of ways for us to put you know different

energy supplies to good use. Are you

exploring small modular nuclear? Yes,

including uh you know with people in

Wyoming. Yeah. Thank you, Mr. Alman. Um

I'm pleased to hear you are releasing an

open Oh, my time's up. Excuse me. It

goes so fast. I'd love to talk to you

about it another time. We're very

excited about it, too. Yeah. Thank you.

I yield back. Thank you, Senator Rosen.

Thank you, Chairman Cruz. I saw ready to

push the button and uh anyway, time does

go by very fast. Thank you for having

this hearing. Um I really believe in the

promise of AI. uh the so exciting um and

we have to ask the right questions in

order to promote its growth on one hand

and how it can explore and and create

these new possibilities and pathways and

also how do we protect ourselves from

bad actors or outcomes as best as we can

know at the time and and uh Mr. Alman,

thank you for spending some time with me

yesterday. I look forward to continuing

to work with you on this. So, I want to

start a little bit today at deepsek and

adversarial AI because in February, I

introduced bipartisan legislation with

Senator Husted to prohibit the using

deepseek on government devices. And

earlier this week, Senator Cassidy and I

introduced a bill that would expand

those prohibitions to include federal

contractors. So, Mr. Smith. Um, what

should our approach be to AI models that

are developed in or by adversarial

countries like the PRC? Should we be

concerned about our adversaries

co-opting AI to promote a particular

ideology, collect sensitive US data? And

how are you combating this um this

threat? Well, I think you can take the

deepseek example and it illustrates it

well. And I think it's just worth um

thinking about the fact that you know

Deep Seek produced two things. They have

a model that is an open- source model

and they have an application, the Deep

Seek app. Um, at Microsoft, we don't

allow our employees to use the Deep Seek

app. We did not put the Deep Seek app in

our uh app store uh because of the kinds

of concerns that you mentioned, namely

data going back to China and the app

creating the kinds of content that I

think people would say um were

associated with Chinese propaganda. At

the same time, because the model itself

is an open-source model, it was possible

for us to go in it, analyze it, and

change the code in the model, which we

and other people have the permission to

do to remove the harmful side effects.

And so I I think we have to you always

think about the different aspects of the

technology. I will say put security

first uh and you know, then go forward

from there. Thank you. I I think we all

know that data is the real power in our

current world. He or she or whomever

owns the data um really can control a

lot of what we do. But I want to move on

and and speak with you Mr. Alman about

AI and anti-semitism a little bit

because earlier this year ADL released a

report showing that several major

generative AI models have perpetuated

dangerous anti-semitic stereotes and

sadly conspiracy theories. So, Mr.

Alman, what steps is industry taking to

ensure that AI models don't perpetuate

anti-semitism? Will you consider

collaborating with civil society to

create kind of a standard benchmark for

AI related to anti-semitism? Uh, use it

as a form of evaluation and then maybe

we could use those for other forms of um

of hate as well. We we of course we we

do collaborate with civil society on

this topic uh and we are excited to

continue to do so. Um, we want our users

to have freedom to use models in the way

they want, but we also don't want them

to be

um, damaging to sort of the fabric of

society or particular groups. There

there there will always be some debate

and the question of free speech in the

context of AI is novel and I think it's

different than what we faced before. We

really do view these as tools for users

one-on-one. Um, but but of course we're

not here to, you know, make horrible

anti-semitic products.

Thank you. Um I want to move on to um

Senator Luhan talked about data center

energy use, water use, something we're

all really concerned about. I want to

put on top of that a little bit about

data uh center security. Add that to the

mix. So last Congress, I actually got a

bill passed into law, my bipartisan

federal data center enhancement act. It

establishes cyber security and

resiliency standards for federal data

centers. And so to Mr. Smith or I'm

sorry, Dr. Sue. Thank you, Dr. Sue. I

want to ask you a little bit about

hardware. Are there ways the hardware

like the chips, AMD designs, new chips

that we're hoping to think about? I know

my career um in in um as a software

developer, we just know things have

gotten smarter, faster, and they just

the cooler they can be, the better we

can compute. So, how can we um make our

chips cooler? How can we make our data

centers, our computing power more

secure? And uh I know interoperability

is sometimes a factor, but can you talk

about this a little bit? Sure. Thank you

for the question, Senator. Uh I look, I

think all of those things are extremely

important. um as you said so in um our

part of the energy efficiency u you know

power constraints that we have from a

chip standpoint you know our job is to

continue to make our chips more and more

efficient um every year uh we've seen

you know 30 times improvement over the

last few years and we will continue uh

to focus um you know in that area and

then to your uh comments about you know

security and ensuring that our chips are

secure and you know people are not um

somehow you know breaking into you know,

those are also very high priorities in

our overall development cycle for future

generationships as well. Well, thank

you. I look forward to working with all

of you again on these important issues,

Mr. Chairman. Thank you, Senator

Sullivan. Thank you, Mr. Chairman. I

want to thank the witnesses for the

testimony today. appreciate the chairman

calling this hearing and I I agree with

Senator Cruz's opening statement about

this is a matter of uh national economic

and national security uh in terms of our

race, however you want to call it,

competition with China. So, um I know

this topic has been pressed, but I want

to I want to just get I want to dig down

a little bit deeper. Uh do you agree

with that all of you? I'm just going to

ask some quick questions that this is a

huge issue of national security,

economic security relative to China and

we as America need to win in that

regard. Very important. Everybody

nodding their head. And then um I know

that been touched but is the consensus

among the witnesses that we are ahead

right now but is uh kind of tentative

lead what would be very quickly we'll

start with you Mr. Alman. What's your

assessment on that? I know we've already

talked about I just want to set the

context for some of the questions. Yeah,

I I believe we are leading the world

right now. I believe we'll continue to

do so. We we want to make AI in the

United States and we want the whole

world to get to benefit from that. I

think that is the strongest thing for

the United States. I think it's also the

right thing to do for all the people of

the world and um I really appreciate you

all being with here with us here today

because I think we'll need your help and

everything you're saying or almost

everything you're saying sounds great.

So,

As I ask this question, I'll ask if you

guys think we're ahead, but then the key

things when you say we need your help,

what would very succinctly, sometimes

we're not so smart up here. Um, what

would the key things be that you would

need from the US government to help us

maintain that lead and dominate this

space, which is what I think we need to

do? Mr. Alman, again to you real quick

on that. We we've talked a little about

infrastructure, but I think we cannot

overstate how important that is and the

ability to have that whole supply chain

or as much of it as possible in the

United States. The previous

technological revolutions have also been

about infrastructure in the supply

chain, but AI is different in terms of

the magnitude of resources that we need.

So projects like Stargate that we're

doing in the US, um things like bringing

chip manufacturing, certainly chip

design to the US, uh permitting power

quickly, like these are critical. if if

we don't get this right, I don't think

anything else we do can help. Um, on on

the model creation side, we've talked

about the need for certainty on our

ability to train and to have fair

footing with the rest of the world to

make sure we can remain competitive. um

the ability to offer products under a

reasonable, fair, light touch regulatory