Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

The post-frontier era: cost, control and compute. Learned a ton in this livestream with Aravind Srinivas, Peter Fenton and Jeffrey Morgan. Big takeaway: the model race is becoming a systems race. Routing, open weight models, local compute, enterprise data, and whether the big labs’ pricing power holds once buyers...

dee_bosa's profile picture

Deirdre Bosa

70,884 subscribers

49,865 görüntüleme • 14 gün önce •via X (Twitter)

Bilim & TeknolojiHaberler & Politika
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Is compute scarcity masking the real economics of AI? interesting point from Peter Fenton: open-weight models are still complex to run well. For now, the big labs have the bundle: model + compute + reliability + access... and thus pricing power. But if compute supply loosens and open model tooling gets easier, routine AI work can more easily move to cheaper/open models.
1:04

Is compute scarcity masking the real economics of AI? interesting point from Peter Fenton: open-weight models are still complex to run well. For now, the big labs have the bundle: model + compute + reliability + access... and thus pricing power. But if compute supply loosens and open model tooling gets easier, routine AI work can more easily move to cheaper/open models.

Deirdre Bosa

47,291 görüntüleme • 14 gün önce

Benchmark’s Peter Fenton says 90%+ of tokens could come from open weight models in the next 18-24 months, pressuring frontier model margins. Full convo at 12p PT/3p ET on the livestream, plus Aravind Srinivas on Perplexity’s new orchestrator model and Jeffrey Morgan on why enterprises are moving toward AI models they can download and control
1:15

Benchmark’s Peter Fenton says 90%+ of tokens could come from open weight models in the next 18-24 months, pressuring frontier model margins. Full convo at 12p PT/3p ET on the livestream, plus Aravind Srinivas on Perplexity’s new orchestrator model and Jeffrey Morgan on why enterprises are moving toward AI models they can download and control

Deirdre Bosa

63,154 görüntüleme • 15 gün önce

“The model alone is no longer the product" Aravind Srinivas says the real product is now the harness around it: orchestration, tools, enterprise context, and cost performance. The post-frontier AI race is about systems, not just the smartest model
0:32

“The model alone is no longer the product" Aravind Srinivas says the real product is now the harness around it: orchestration, tools, enterprise context, and cost performance. The post-frontier AI race is about systems, not just the smartest model

Deirdre Bosa

101,506 görüntüleme • 15 gün önce

"It all comes down to compute." Dmitri Alperovitch from Silverado Policy Accelerator explains: "The single most important input to winning is compute the processing power used to train and run AI models. Let me say that plainly, because it is defining that everything that congress and this committee do on AI policy. The binding constraint in this competition is not talent, it is not data, and it is not cash. Both the United States and China have talented researchers and financial resources, and we have learned that frontier models trained on generic data routinely outperform smaller models, trained on more specialized inputs. It all comes down to compute."
0:33

"It all comes down to compute." Dmitri Alperovitch from Silverado Policy Accelerator explains: "The single most important input to winning is compute the processing power used to train and run AI models. Let me say that plainly, because it is defining that everything that congress and this committee do on AI policy. The binding constraint in this competition is not talent, it is not data, and it is not cash. Both the United States and China have talented researchers and financial resources, and we have learned that frontier models trained on generic data routinely outperform smaller models, trained on more specialized inputs. It all comes down to compute."

Select Committee on China

41,578 görüntüleme • 3 ay önce

A crypto project actually trained a 72B parameter AI model from scratch using decentralized GPU compute. Not fine-tuned, not a wrapper: trained from zero. The model benchmarks competitively against Meta's LLaMA 3 on reasoning tasks, and the entire training run cost a fraction of what centralized labs spend. If decentralized compute can produce frontier-class models, the moat around OpenAI and Anthropic is thinner than people think.
3:28

A crypto project actually trained a 72B parameter AI model from scratch using decentralized GPU compute. Not fine-tuned, not a wrapper: trained from zero. The model benchmarks competitively against Meta's LLaMA 3 on reasoning tasks, and the entire training run cost a fraction of what centralized labs spend. If decentralized compute can produce frontier-class models, the moat around OpenAI and Anthropic is thinner than people think.

VirtualBacon

40,543 görüntüleme • 3 ay önce

Why wouldn’t China want more data centers built in the United States? Simple, the nation that leads in AI will lead the future, economically, technologically, and militarily. We’re already seeing it happen in real time as AI drives unprecedented productivity and margin expansion across every sector of the economy. While America debates permits, regulations, and protests over data centers, China is rapidly building power infrastructure and scaling compute capacity as fast as possible. This race is no longer theoretical. Whoever has the most compute, the best models, and the strongest infrastructure will shape the next era of global power.
1:51

Why wouldn’t China want more data centers built in the United States? Simple, the nation that leads in AI will lead the future, economically, technologically, and militarily. We’re already seeing it happen in real time as AI drives unprecedented productivity and margin expansion across every sector of the economy. While America debates permits, regulations, and protests over data centers, China is rapidly building power infrastructure and scaling compute capacity as fast as possible. This race is no longer theoretical. Whoever has the most compute, the best models, and the strongest infrastructure will shape the next era of global power.

Kevin O'Leary aka Mr. Wonderful

35,475 görüntüleme • 2 ay önce

DeepSeek has changed everything we thought we knew about LLMs and the AI race between the US and China. A preview of our TechCheck deep dive on the mysterious AI lab with insights from Aravind Srinivas & Chetan Puttagunta Link to full piece below
0:51

DeepSeek has changed everything we thought we knew about LLMs and the AI race between the US and China. A preview of our TechCheck deep dive on the mysterious AI lab with insights from Aravind Srinivas & Chetan Puttagunta Link to full piece below

Deirdre Bosa

149,914 görüntüleme • 1 yıl önce

Larry Ellison says Oracle is building nuclear reactors to power "acres" of GPU clusters and it will cost companies $100 billion in the next 3 years to build a frontier AI model and stay in the race
1:09

Larry Ellison says Oracle is building nuclear reactors to power "acres" of GPU clusters and it will cost companies $100 billion in the next 3 years to build a frontier AI model and stay in the race

Tsarathustra

1,017,124 görüntüleme • 1 yıl önce

As AI labs race to train and deploy new frontier models, existing models become more affordable with better tokenomics. ✨ "Everybody's trying to get to the next frontier. And every time they get to the next frontier, the last generation AI tokens, the cost starts to decline about a factor of 10x every year," said NVIDIA CEO Jensen Huang in a recent keynote. Model optimization techniques such as speculative decoding and multi-token prediction, combined with inference serving platforms like NVIDIA Dynamo on NVIDIA Blackwell NVL72 systems, enable AI factories to boost throughput by 10x with one-tenth of the cost per token. Learn more about AI factory tokenomics ➡️
0:45

As AI labs race to train and deploy new frontier models, existing models become more affordable with better tokenomics. ✨ "Everybody's trying to get to the next frontier. And every time they get to the next frontier, the last generation AI tokens, the cost starts to decline about a factor of 10x every year," said NVIDIA CEO Jensen Huang in a recent keynote. Model optimization techniques such as speculative decoding and multi-token prediction, combined with inference serving platforms like NVIDIA Dynamo on NVIDIA Blackwell NVL72 systems, enable AI factories to boost throughput by 10x with one-tenth of the cost per token. Learn more about AI factory tokenomics ➡️

NVIDIA AI

16,053 görüntüleme • 6 ay önce

Sundar Pichai says AI will not be controlled by one company or a small group of companies The field is too dynamic, with big labs, startups, open-source models, and governments all becoming part of the race "AI is unlike any technology before it" Its power means it cannot be built separately from the rest of society
0:42

Sundar Pichai says AI will not be controlled by one company or a small group of companies The field is too dynamic, with big labs, startups, open-source models, and governments all becoming part of the race "AI is unlike any technology before it" Its power means it cannot be built separately from the rest of society

Haider.

33,018 görüntüleme • 2 ay önce

China is once again unsettling its American competitors in the AI race. Chinese labs have returned to the spotlight with the unveiling of GLM 5.2, described as the most powerful AI model ever trained in China — and one of the leading open‑source models worldwide. 🔍 Key highlights of “GLM 5.2”: ♦️ It is considered the strongest AI model developed in China to date, and ranks among the smartest open‑source models available. ♦️ It operates at a cost less than one‑tenth that of Anthropic’s latest models, making it a far more economical option. ♦️ It is likely to attract developers and companies seeking powerful, low‑cost models — especially amid growing technical and geopolitical restrictions. ♦️ Some evaluations place the model among the top globally, trailing OpenAI’s models while outperforming several competitors in specialized benchmarks and performance tests.
0:42

China is once again unsettling its American competitors in the AI race. Chinese labs have returned to the spotlight with the unveiling of GLM 5.2, described as the most powerful AI model ever trained in China — and one of the leading open‑source models worldwide. 🔍 Key highlights of “GLM 5.2”: ♦️ It is considered the strongest AI model developed in China to date, and ranks among the smartest open‑source models available. ♦️ It operates at a cost less than one‑tenth that of Anthropic’s latest models, making it a far more economical option. ♦️ It is likely to attract developers and companies seeking powerful, low‑cost models — especially amid growing technical and geopolitical restrictions. ♦️ Some evaluations place the model among the top globally, trailing OpenAI’s models while outperforming several competitors in specialized benchmarks and performance tests.

China pulse 🇨🇳

14,018 görüntüleme • 26 gün önce

Our most exciting episode of Training Data yet 🍓🍰 OpenAI’s o1 represents a major leap forward by giving models time to "think." Inference-time compute is the next big research frontier. Thrilled to have Noam Brown, ilge, and hunter on the show Pat Grady Sequoia Capital
1:23

Our most exciting episode of Training Data yet 🍓🍰 OpenAI’s o1 represents a major leap forward by giving models time to "think." Inference-time compute is the next big research frontier. Thrilled to have Noam Brown, ilge, and hunter on the show Pat Grady Sequoia Capital

Sonya Huang 🐥

51,628 görüntüleme • 1 yıl önce

There's an economics theorem called Alchian-Allen. And it has the very interesting implication that AI labs will be able to charge *higher* margins on their best models as compute gets scarcer. As compute gets more expensive, the cost of running any model goes up. So you might as well pay a bit more to make sure you're running the very best model. Which means the economics of being at the frontier improve, because if you’re not running the very best model, then you’re underutilizing this very precious compute. This pushes the AI model market towards winner-take-all; if you're the best, you can get away with charging an even higher margin. Dylan Patel tells me that we’re already seeing this today: all the revenue in the industry is on the best models. That’s the Alchian-Allen effect. If there’s a cost increase that’s roughly the same for all products, then the relative difference in price between higher and lower quality goods actually goes down. Consumers become relatively more willing to pay for the premium product. And it means that as the compute shortage hits, AI labs can capture more margin - not less, as you might expect - because consumers are choosing premium models more often.
1:21

There's an economics theorem called Alchian-Allen. And it has the very interesting implication that AI labs will be able to charge *higher* margins on their best models as compute gets scarcer. As compute gets more expensive, the cost of running any model goes up. So you might as well pay a bit more to make sure you're running the very best model. Which means the economics of being at the frontier improve, because if you’re not running the very best model, then you’re underutilizing this very precious compute. This pushes the AI model market towards winner-take-all; if you're the best, you can get away with charging an even higher margin. Dylan Patel tells me that we’re already seeing this today: all the revenue in the industry is on the best models. That’s the Alchian-Allen effect. If there’s a cost increase that’s roughly the same for all products, then the relative difference in price between higher and lower quality goods actually goes down. Consumers become relatively more willing to pay for the premium product. And it means that as the compute shortage hits, AI labs can capture more margin - not less, as you might expect - because consumers are choosing premium models more often.

Dwarkesh Patel

322,651 görüntüleme • 4 ay önce

🔥BESSENT: "AMERICA WILL SOON CONTROL 80% OF GLOBAL COMPUTE" Treasury Secretary Scott Bessent said the US is roughly a year ahead of China in AI and that its share of global compute power will grow from around 60% to 80%. Bessent is personally leading the White House AI effort and says losing the race to China would be "unconscionable."
1:16

🔥BESSENT: "AMERICA WILL SOON CONTROL 80% OF GLOBAL COMPUTE" Treasury Secretary Scott Bessent said the US is roughly a year ahead of China in AI and that its share of global compute power will grow from around 60% to 80%. Bessent is personally leading the White House AI effort and says losing the race to China would be "unconscionable."

Coin Bureau

105,202 görüntüleme • 6 gün önce

When we first met Tom, his obsession with energy markets came through immediately. Seemed random, but it's "actually" central to what he's building at Actual Computer. The thesis is that local inference is inevitable. Open source models are getting good enough, people don't want to feed their thoughts to AI labs, and demand for compute will continue to be insatiable. But the main forcing function is that chips aren't the bottleneck anymore - power is. Compute is derivative of energy, and the massive data center buildout has created an energy shortage where GPUs sit idle waiting for power to come online. Yet one place that already has power, and always will, is everywhere else. Homes. Businesses. Universities. Collectively, they have more compute than all the data centers combined. Tom Lynch goal is to build a distributed network of people plugging in their local compute (devices like Mac minis to consumer Nvidia cards) to serve inference demand. The substrate he's chosen is Bittensor, on Subnet 95. Actual Computer has an exceptional team behind it, and this is one of the projects that's gotten me most excited in a long time. Enjoy this conversation with the two of us!
37:17

When we first met Tom, his obsession with energy markets came through immediately. Seemed random, but it's "actually" central to what he's building at Actual Computer. The thesis is that local inference is inevitable. Open source models are getting good enough, people don't want to feed their thoughts to AI labs, and demand for compute will continue to be insatiable. But the main forcing function is that chips aren't the bottleneck anymore - power is. Compute is derivative of energy, and the massive data center buildout has created an energy shortage where GPUs sit idle waiting for power to come online. Yet one place that already has power, and always will, is everywhere else. Homes. Businesses. Universities. Collectively, they have more compute than all the data centers combined. Tom Lynch goal is to build a distributed network of people plugging in their local compute (devices like Mac minis to consumer Nvidia cards) to serve inference demand. The substrate he's chosen is Bittensor, on Subnet 95. Actual Computer has an exceptional team behind it, and this is one of the projects that's gotten me most excited in a long time. Enjoy this conversation with the two of us!

Sami Kassab

35,706 görüntüleme • 6 ay önce

In the 20th century, power depended on OIL and STEEL. In the 21st century, power depends on AI, CHIPS and COMPUTE CAPABILITY. At AI Summit 2026 India, I spoke about why the GPU challenge is not just a ‘supply chain issue’ but a ‘sovereignty issue’. In the AI century, power will rest with those who control chips, compute capacity and data centres. Today, design monopolies, manufacturing concentration and export controls determine who gets access. India controls none of these critical levers. We have the talent. We have the ambition. We have the intent. We have the capital. But talent without compute is aspiration. And compute without sovereignty is dependence. The role of policymakers is not to slow AI down; it is to remove bottlenecks, diversify access, set clear national targets, and build sovereign AI infrastructure in India. This is not partisan. It is strategic. #IndiaAIImpactSummit2026 #AI #ResponsibleAI #ArtificialIntelligence #BharatMandapam
3:41

In the 20th century, power depended on OIL and STEEL. In the 21st century, power depends on AI, CHIPS and COMPUTE CAPABILITY. At AI Summit 2026 India, I spoke about why the GPU challenge is not just a ‘supply chain issue’ but a ‘sovereignty issue’. In the AI century, power will rest with those who control chips, compute capacity and data centres. Today, design monopolies, manufacturing concentration and export controls determine who gets access. India controls none of these critical levers. We have the talent. We have the ambition. We have the intent. We have the capital. But talent without compute is aspiration. And compute without sovereignty is dependence. The role of policymakers is not to slow AI down; it is to remove bottlenecks, diversify access, set clear national targets, and build sovereign AI infrastructure in India. This is not partisan. It is strategic. #IndiaAIImpactSummit2026 #AI #ResponsibleAI #ArtificialIntelligence #BharatMandapam

Raghav Chadha

70,153 görüntüleme • 5 ay önce

⚡Why Edge Compute Matters for the Future of Agentic AI AI isn’t just about smarter models, it’s about where they run. Centralized clouds are costly, slow, and controlled by a few. That’s not the future. 👉Join the OptimAI Network: With OptimAI Edge Compute and the upcoming Core Node release, every device becomes part of a decentralized supercomputer: + AI models run directly on your devices (phones, desktops, IoT devices) + Data stays local, secure, and real-time + Compute scales with the community, not corporations This is how we power the next generation of Agentic AI - AI systems that don’t just think, but act like you. Lightweight, fast, everywhere, for everyone. Stay tuned. The Edge is coming.
0:29

⚡Why Edge Compute Matters for the Future of Agentic AI AI isn’t just about smarter models, it’s about where they run. Centralized clouds are costly, slow, and controlled by a few. That’s not the future. 👉Join the OptimAI Network: With OptimAI Edge Compute and the upcoming Core Node release, every device becomes part of a decentralized supercomputer: + AI models run directly on your devices (phones, desktops, IoT devices) + Data stays local, secure, and real-time + Compute scales with the community, not corporations This is how we power the next generation of Agentic AI - AI systems that don’t just think, but act like you. Lightweight, fast, everywhere, for everyone. Stay tuned. The Edge is coming.

OptimAI Network

43,596 görüntüleme • 10 ay önce

Access codes will go out tomorrow via welcome emails. API status updates and full API access will follow on Friday. HdeAPoHivsm9MZfeY5tW7apJEprc8Fs594bWmnzfpump The $ICPX website has been rebuilt from the ground up and it reflects exactly where this protocol is headed. The new site is the gateway to decentralised compute powered by Nvidia and Google GPU cloud partner programs, meaning whenever you rent a GPU for a job, it is always available. No downtime, no waitlists. Enterprise grade H100s, H200s and RTX 4090s. Accessible to anyone, at a fraction of what centralised providers charge. Pay with $ICPX tokens and get immediate access to serious compute power. Stake $ICPX to unlock deeper discounts and watch your costs drop over time the more committed you are to the network. This is what pay-per-job decentralised compute actually looks like in practice. Full control over training and running your models, with a lean 0.25% protocol fee managed by multisig. Open-source, immutable, and formally verified with Kani. $
0:35

Access codes will go out tomorrow via welcome emails. API status updates and full API access will follow on Friday. HdeAPoHivsm9MZfeY5tW7apJEprc8Fs594bWmnzfpump The $ICPX website has been rebuilt from the ground up and it reflects exactly where this protocol is headed. The new site is the gateway to decentralised compute powered by Nvidia and Google GPU cloud partner programs, meaning whenever you rent a GPU for a job, it is always available. No downtime, no waitlists. Enterprise grade H100s, H200s and RTX 4090s. Accessible to anyone, at a fraction of what centralised providers charge. Pay with $ICPX tokens and get immediate access to serious compute power. Stake $ICPX to unlock deeper discounts and watch your costs drop over time the more committed you are to the network. This is what pay-per-job decentralised compute actually looks like in practice. Full control over training and running your models, with a lean 0.25% protocol fee managed by multisig. Open-source, immutable, and formally verified with Kani. $

ICPX Protocol

32,161 görüntüleme • 1 ay önce

Chamath is making one of the most important business arguments of 2026. Half of large US companies right now cannot generate returns that exceed their cost of capital, which has normalized back to its long run average of 8 to 11%. Another one in seven companies globally is stuck generating persistent returns between 1 and 5% and most businesses don't have room for error and in this environment walks every frontier AI lab saying the same thing, give us your data, your workflows, your processes and our model will make everything better. And companies by the millions said yes. What they didn't fully account for is what happens on the other side of that door. Every time an employee runs a query through a frontier model API, the prompt goes through external servers, workflows, customer data, pricing logic, internal processes, all of it transmitted through a third party. As Alex Karp said companies are spending on tokens while handing over the exact proprietary advantages that make their business worth owning. Microsoft blocked internal use of Anthropic's Claude Fable 5 but over its 30-day data retention policy and the largest software company in the world decided a frontier model's data handling was too risky for its own employees. A US government action revoked access to another frontier model for foreign nationals overnight. Now here's where the cost math becomes impossible to ignore. Deutsche Bank calculated a roughly 65x cost gap between frontier models like Claude Fable 5 at ~$3.25 per task and open-source alternatives at ~$0.05. For 90% of everyday enterprise tasks, performance is comparable. Open-weight models now match closed frontier systems on core agent tasks at roughly one-tenth the cost, a high-volume deployment that costs $250/day on Claude runs at $12/day on an open-source equivalent. Chamath Palihapitiya tested this directly by running a standard enterprise code migration task through an orchestration layer wrapping an open-source model came in 16.4x cheaper than using a frontier model directly.
5:24

Chamath is making one of the most important business arguments of 2026. Half of large US companies right now cannot generate returns that exceed their cost of capital, which has normalized back to its long run average of 8 to 11%. Another one in seven companies globally is stuck generating persistent returns between 1 and 5% and most businesses don't have room for error and in this environment walks every frontier AI lab saying the same thing, give us your data, your workflows, your processes and our model will make everything better. And companies by the millions said yes. What they didn't fully account for is what happens on the other side of that door. Every time an employee runs a query through a frontier model API, the prompt goes through external servers, workflows, customer data, pricing logic, internal processes, all of it transmitted through a third party. As Alex Karp said companies are spending on tokens while handing over the exact proprietary advantages that make their business worth owning. Microsoft blocked internal use of Anthropic's Claude Fable 5 but over its 30-day data retention policy and the largest software company in the world decided a frontier model's data handling was too risky for its own employees. A US government action revoked access to another frontier model for foreign nationals overnight. Now here's where the cost math becomes impossible to ignore. Deutsche Bank calculated a roughly 65x cost gap between frontier models like Claude Fable 5 at ~$3.25 per task and open-source alternatives at ~$0.05. For 90% of everyday enterprise tasks, performance is comparable. Open-weight models now match closed frontier systems on core agent tasks at roughly one-tenth the cost, a high-volume deployment that costs $250/day on Claude runs at $12/day on an open-source equivalent. Chamath Palihapitiya tested this directly by running a standard enterprise code migration task through an orchestration layer wrapping an open-source model came in 16.4x cheaper than using a frontier model directly.

Milk Road AI

280,929 görüntüleme • 20 gün önce

🇺🇸 Elon confirms the “Terafab” model links xAI, SpaceX, and Tesla to scale chips, energy, and factories together, aiming for terawatt-level compute output. The idea is to control the full stack: chip design, manufacturing, power generation, and deployment, with most compute eventually supporting space-based systems. So it’s like a feedback loop, more factories build more chips, which train better AI, which then designs even better factories. Because why build a factory… when you can try to build the entire stack. Source: Elon Musk Tesla
1:45

🇺🇸 Elon confirms the “Terafab” model links xAI, SpaceX, and Tesla to scale chips, energy, and factories together, aiming for terawatt-level compute output. The idea is to control the full stack: chip design, manufacturing, power generation, and deployment, with most compute eventually supporting space-based systems. So it’s like a feedback loop, more factories build more chips, which train better AI, which then designs even better factories. Because why build a factory… when you can try to build the entire stack. Source: Elon Musk Tesla

Mario Nawfal

152,538 görüntüleme • 4 ay önce