Загрузка видео...

Не удалось загрузить видео

На главную

“Reasoning has fundamentally changed the economics of these frontier models.” Gavin Baker says reasoning lets scaled user bases unlock a new flywheel. Users improve the model, and the model improves the product. Gavin Baker

a16z's profile picture

a16z

1,001,611 subscribers

23,671 просмотров • 10 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

“Is there an AI bubble?” Gavin Baker and David George In this conversation from a16z’s Runtime conference, Gavin Baker, Managing Partner and CIO of Atreides Management, joins David George, General Partner at a16z, to unpack the macro view of AI: the trillion-dollar data center buildout, the new economics of GPUs, and what this boom means for investors, founders, and the global economy. They discuss how this cycle compares to the dot-com era, why “there are no dark GPUs,” and what makes today’s infrastructure spending different from past bubbles. Gavin explains why he believes we’re still early in the AI supercycle, the changing margins in SaaS and software, and how business models and consumer interfaces are being rewritten in real time. 00:00 Intro 01:02 Are we in an AI Bubble? 02:41 Dark fiber vs. “no dark GPUs” 05:07 ROI on AI: Why this time is different 08:36 Round-tripping deals 12:22 The application layer: It’s still early 15:24 Margins, scaling laws 23:26 Reasoning models and the flywheel 27:18 The future of business models 29:41 Robotics and Elon’s Optimus vision Gavin Baker David George
31:52

“Is there an AI bubble?” Gavin Baker and David George In this conversation from a16z’s Runtime conference, Gavin Baker, Managing Partner and CIO of Atreides Management, joins David George, General Partner at a16z, to unpack the macro view of AI: the trillion-dollar data center buildout, the new economics of GPUs, and what this boom means for investors, founders, and the global economy. They discuss how this cycle compares to the dot-com era, why “there are no dark GPUs,” and what makes today’s infrastructure spending different from past bubbles. Gavin explains why he believes we’re still early in the AI supercycle, the changing margins in SaaS and software, and how business models and consumer interfaces are being rewritten in real time. 00:00 Intro 01:02 Are we in an AI Bubble? 02:41 Dark fiber vs. “no dark GPUs” 05:07 ROI on AI: Why this time is different 08:36 Round-tripping deals 12:22 The application layer: It’s still early 15:24 Margins, scaling laws 23:26 Reasoning models and the flywheel 27:18 The future of business models 29:41 Robotics and Elon’s Optimus vision Gavin Baker David George

a16z

92,161 просмотров • 10 месяцев назад

Apple's AI Reasoning Model Paper Explained Apple’s disruptive new AI reasoning model research paper, “The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models” explained, and what it means for AGI.
3:22

Apple's AI Reasoning Model Paper Explained Apple’s disruptive new AI reasoning model research paper, “The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models” explained, and what it means for AGI.

Harper Carroll

37,956 просмотров • 1 год назад

Elon (Musk) has done more for the planet and de-carbonizing it than all the activists and Greta Thunbergs..." "Global Warming is a solved problem...only through economics!" -- Gavin Baker Full episode below
0:39

Elon (Musk) has done more for the planet and de-carbonizing it than all the activists and Greta Thunbergs..." "Global Warming is a solved problem...only through economics!" -- Gavin Baker Full episode below

Michael Eisenberg

151,258 просмотров • 10 месяцев назад

Gavin Baker Gavin Baker says open source is "awesome" for AI infrastructure names because it shifts the economic value from the frontier labs to the infrastructure, and it is already 80% plus of all tokens processed. "A misconception that a lot of people have is that open source models are somehow bad for AI. They're awesome for the AI infrastructure providers. They just shift economic value from the margins of the frontier labs to the infrastructure." "But I do think there's still a role for these frontier models. And it may be true, to date, frontier tokens are capturing 90% of the economic value, and open source tokens are probably 80% plus of tokens processed, and those ratios may be here to stay." _______ Follow Fireside Alpha for more highlights of the best business and technology conversations.
0:37

Gavin Baker Gavin Baker says open source is "awesome" for AI infrastructure names because it shifts the economic value from the frontier labs to the infrastructure, and it is already 80% plus of all tokens processed. "A misconception that a lot of people have is that open source models are somehow bad for AI. They're awesome for the AI infrastructure providers. They just shift economic value from the margins of the frontier labs to the infrastructure." "But I do think there's still a role for these frontier models. And it may be true, to date, frontier tokens are capturing 90% of the economic value, and open source tokens are probably 80% plus of tokens processed, and those ratios may be here to stay." _______ Follow Fireside Alpha for more highlights of the best business and technology conversations.

Fireside Alpha

162,832 просмотров • 1 месяц назад

OpenAI CFO Sarah Friar says lawyers are reporting that the new o1 reasoning model can do the work of a $2000/hour paralegal
0:36

OpenAI CFO Sarah Friar says lawyers are reporting that the new o1 reasoning model can do the work of a $2000/hour paralegal

Tsarathustra

934,400 просмотров • 1 год назад

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture
0:59

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture

Casper Hansen

313,371 просмотров • 1 год назад

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.
6:06

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.

NVIDIA AI

14,777 просмотров • 12 дней назад

$GOOGL fell 7-10% on its first negative free cash flow quarter since IPO. Chamath Palihapitiya Chamath Palihapitiya says buy the machine. Google has compounded capital at roughly 32% ROIC for 25 years, and it just guided capex to $195-205B. The Street read a red flag. Chamath reads a compounder spending into its lead. The deeper point - frontier models now commoditize within weeks, so value drains from the model layer toward infrastructure. That fragmentation hurts Anthropic and OpenAI and helps Google, which monetizes at silicon and cloud no matter which model wins. Cloud grew 82% on a $100B run rate. Gavin Baker Gavin Baker has argued hyperscaler capex is rational investment, not waste - the same read. The call - the negative-FCF print is an entry into the cleanest way to own the AI buildout without betting on a single model. Why model-layer commoditization is a tailwind for $GOOGL: Source: All-In Podcast -
6:11

$GOOGL fell 7-10% on its first negative free cash flow quarter since IPO. Chamath Palihapitiya Chamath Palihapitiya says buy the machine. Google has compounded capital at roughly 32% ROIC for 25 years, and it just guided capex to $195-205B. The Street read a red flag. Chamath reads a compounder spending into its lead. The deeper point - frontier models now commoditize within weeks, so value drains from the model layer toward infrastructure. That fragmentation hurts Anthropic and OpenAI and helps Google, which monetizes at silicon and cloud no matter which model wins. Cloud grew 82% on a $100B run rate. Gavin Baker Gavin Baker has argued hyperscaler capex is rational investment, not waste - the same read. The call - the negative-FCF print is an entry into the cleanest way to own the AI buildout without betting on a single model. Why model-layer commoditization is a tailwind for $GOOGL: Source: All-In Podcast -

Podcast Alpha

42,627 просмотров • 1 месяц назад

Interesting that in three of my recent conversations with Krishna at Anthropic, Dylan Patel, and Gavin Baker, each said that frontier tokens are capturing the majority of the economic value. Gavin: "An overwhelming amount of the economic returns to AI at the model layer have been at the frontier. That's surprising to me, and I think it's been surprising to a lot of people. This is one of the most important questions to be answered, and you need to have a hypothesis on it as an investor." Krishna: "We think the returns to frontier intelligence are extremely high. Customers invest really heavily in more tokens with the newer models. The ones at the frontier clearly are capturing this economic value, driving meaningful ROI for customers. The returns to frontier intelligence are not slowing down." Dylan: "No one gives a crap about GPT-4 class models. They want the frontier because the frontier lets them create the economically valuable things."
2:08

Interesting that in three of my recent conversations with Krishna at Anthropic, Dylan Patel, and Gavin Baker, each said that frontier tokens are capturing the majority of the economic value. Gavin: "An overwhelming amount of the economic returns to AI at the model layer have been at the frontier. That's surprising to me, and I think it's been surprising to a lot of people. This is one of the most important questions to be answered, and you need to have a hypothesis on it as an investor." Krishna: "We think the returns to frontier intelligence are extremely high. Customers invest really heavily in more tokens with the newer models. The ones at the frontier clearly are capturing this economic value, driving meaningful ROI for customers. The returns to frontier intelligence are not slowing down." Dylan: "No one gives a crap about GPT-4 class models. They want the frontier because the frontier lets them create the economically valuable things."

Patrick OShaughnessy

121,110 просмотров • 3 месяцев назад

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.
0:29

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Affine

14,866 просмотров • 2 месяцев назад

"If we do not all become masters of the machine gun, we're going to get mastered." Gavin Baker on why it's time to develop and fine-tune your AI skills, plus the wisdom of Tom Cruise's "The Last Samurai." cc: Gavin Baker, Tom Cruise, Invest Like the Best, Patrick OShaughnessy
1:31

"If we do not all become masters of the machine gun, we're going to get mastered." Gavin Baker on why it's time to develop and fine-tune your AI skills, plus the wisdom of Tom Cruise's "The Last Samurai." cc: Gavin Baker, Tom Cruise, Invest Like the Best, Patrick OShaughnessy

This Week in Startups

18,473 просмотров • 3 месяцев назад

AI Bull vs Bear #1: 60-70% gross margins on AI inference. Gavin Baker Gavin Baker of Atreides ran the math on BG2 Pod: inference revenue exits 2026 above $200B, and he calls $300B a low estimate for 2027. Ed Zitron's Ed Zitron bear case says costs scale with revenue, so the curve never bends. Baker's number says the unit economics already work at the inference layer. The catch: that is gross margin, not the whole P&L. It does not answer OpenAI's $21B operating loss. Where the bull margin math meets Zitron's receipts:
5:16

AI Bull vs Bear #1: 60-70% gross margins on AI inference. Gavin Baker Gavin Baker of Atreides ran the math on BG2 Pod: inference revenue exits 2026 above $200B, and he calls $300B a low estimate for 2027. Ed Zitron's Ed Zitron bear case says costs scale with revenue, so the curve never bends. Baker's number says the unit economics already work at the inference layer. The catch: that is gross margin, not the whole P&L. It does not answer OpenAI's $21B operating loss. Where the bull margin math meets Zitron's receipts:

Podcast Alpha

15,261 просмотров • 2 месяцев назад

OpenAI researcher Noam Brown on hallucination with the new IMO reasoning model: > Mathematicians used to comb through model solutions because earlier systems would quietly flip an inequality or tuck in a wrong step, creating hallucinated answers. > Brown says the updated IMO reasoning model now tends to say “I’m not sure” whenever it lacks a valid proof, which sharply cuts down on those hidden errors. TLDR, the model shows a clear shift away from hallucinations and toward reliable, self‑aware reasoning.
0:39

OpenAI researcher Noam Brown on hallucination with the new IMO reasoning model: > Mathematicians used to comb through model solutions because earlier systems would quietly flip an inequality or tuck in a wrong step, creating hallucinated answers. > Brown says the updated IMO reasoning model now tends to say “I’m not sure” whenever it lacks a valid proof, which sharply cuts down on those hidden errors. TLDR, the model shows a clear shift away from hallucinations and toward reliable, self‑aware reasoning.

Chris

230,471 просмотров • 1 год назад

xAI charges $50B per gigawatt. Neoclouds charge $17-25B. Gavin Baker Gavin Baker of Atreides Management told John Coogan and Jordi Hays on TBPN that Mars is not the SpaceX bull case. Altimeter's research shows xAI monetizes compute at $50B per gigawatt on the Google deal - 2-3x what any neocloud competitor charges. Baker stayed long through the IPO. His 12-month model doesn't track rocket launches. It tracks gigawatt additions. xAI also ordered roughly 20% of NVIDIA's Ruben production. Ruben is easier to deploy than Blackwell. Each new gigawatt at that pricing premium is a significant revenue event. Model gigawatts, not launch cadence. That's the trade. Full breakdown of Baker's near-term SpaceX case: Source: TBPN -
1:14

xAI charges $50B per gigawatt. Neoclouds charge $17-25B. Gavin Baker Gavin Baker of Atreides Management told John Coogan and Jordi Hays on TBPN that Mars is not the SpaceX bull case. Altimeter's research shows xAI monetizes compute at $50B per gigawatt on the Google deal - 2-3x what any neocloud competitor charges. Baker stayed long through the IPO. His 12-month model doesn't track rocket launches. It tracks gigawatt additions. xAI also ordered roughly 20% of NVIDIA's Ruben production. Ruben is easier to deploy than Blackwell. Each new gigawatt at that pricing premium is a significant revenue event. Model gigawatts, not launch cadence. That's the trade. Full breakdown of Baker's near-term SpaceX case: Source: TBPN -

Podcast Alpha

54,609 просмотров • 2 месяцев назад

Sam Altman says AI reasoning is still at the GPT-2 stage but the improvement curve is steep and the new o1 model represents a new paradigm of AI development which will enable rapid progress in capabilities
2:07

Sam Altman says AI reasoning is still at the GPT-2 stage but the improvement curve is steep and the new o1 model represents a new paradigm of AI development which will enable rapid progress in capabilities

Tsarathustra

419,003 просмотров • 1 год назад