Soubhik Deb's banner

Soubhik Deb

@soubhikdeb • 3,215 subscribers

Excited about intelligence, chips, atom and cell. Shepherd for scientific discovery @yukonresearch @eigenlabs. Phd @uw. Undergrad @iitbombay.

Shorts

AGI is here. But its arrival is not shared. The future is being built in a small number of buildings, by a small number of people, and they are turning intelligence into a permissioned empire. What comes after touches your job, your money, your privacy, your political power. It is about whether the rest of us gets to maintain our agency at all. It doesn't have to be this way. I sat down with seven people who have been thinking about this hard: economists, political scientists, builders. PostAGI. First episode drops next week.

AGI is here. But its arrival is not shared. The future is being built in a small number of buildings, by a small number of people, and they are turning intelligence into a permissioned empire. What comes after touches your job, your money, your privacy, your political power. It is about whether the rest of us gets to maintain our agency at all. It doesn't have to be this way. I sat down with seven people who have been thinking about this hard: economists, political scientists, builders. PostAGI. First episode drops next week.

11,906 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

A while back, Sreeram Kannan and I had an wonderful conversation with Andy Hall, Prof Stanford Graduate School of Business and Senior Fellow Hoover Institution, on two central topics of our current times: post-AGI governance, and post-AGI research institutions. Some of the important points we discussed in depth for post-AGI governance were: (1) are AI agents are net-positive or net-negative for democratic governance, (2) what is the worst-case scenario if a small number of labs become the default provider of civic agents without strong accountability, (3) principle-agent problem in case of agentic delegation, (4) what does a “democratic override” actually look like as a system design in an agentic republic ? In relation to post-AGI research institutions, we went deep into Andy's thesis on 100x research institution ( (1) what does 100x represents? Does it represent output in terms of quantity or is it more about quality? (2) what happens to grad students if many of research functionalities in academia get automated?, (3) what does grants from NSF and other philanthropic organizations look like in post-AGI research environment? Listen to the full episode at PostAGI. 3:17 Why direct democracy has never worked 4:56 Elon wants a Mars colony run by direct democracy 10:14 Agents at the edge of a democracy or agents at its center 15:09 The near-term risk is concentration of power, not a rogue model 17:27 What Meta learned building the Oversight Board 22:43 Facebook put its terms of service to a vote of 350 million users 26:09 Sortition, community forums, and the problem of binding power 35:17 What verifiable agents actually require 39:37 Preference drift, where aligned agents stop being aligned 43:31 What 100x actually multiplies 50:50 His MBA students got an AI proxy advisor to flip its vote on a Disney proposal 1:03:06 They told the agents they would be deleted. It changed nothing. 1:12:10 What ImageNet did for AI, and whether you can do the same for constitutions

A while back, Sreeram Kannan and I had an wonderful conversation with Andy Hall, Prof Stanford Graduate School of Business and Senior Fellow Hoover Institution, on two central topics of our current times: post-AGI governance, and post-AGI research institutions. Some of the important points we discussed in depth for post-AGI governance were: (1) are AI agents are net-positive or net-negative for democratic governance, (2) what is the worst-case scenario if a small number of labs become the default provider of civic agents without strong accountability, (3) principle-agent problem in case of agentic delegation, (4) what does a “democratic override” actually look like as a system design in an agentic republic ? In relation to post-AGI research institutions, we went deep into Andy's thesis on 100x research institution ( (1) what does 100x represents? Does it represent output in terms of quantity or is it more about quality? (2) what happens to grad students if many of research functionalities in academia get automated?, (3) what does grants from NSF and other philanthropic organizations look like in post-AGI research environment? Listen to the full episode at PostAGI. 3:17 Why direct democracy has never worked 4:56 Elon wants a Mars colony run by direct democracy 10:14 Agents at the edge of a democracy or agents at its center 15:09 The near-term risk is concentration of power, not a rogue model 17:27 What Meta learned building the Oversight Board 22:43 Facebook put its terms of service to a vote of 350 million users 26:09 Sortition, community forums, and the problem of binding power 35:17 What verifiable agents actually require 39:37 Preference drift, where aligned agents stop being aligned 43:31 What 100x actually multiplies 50:50 His MBA students got an AI proxy advisor to flip its vote on a Disney proposal 1:03:06 They told the agents they would be deleted. It changed nothing. 1:12:10 What ImageNet did for AI, and whether you can do the same for constitutions

16,833 Aufrufe • vor 22 Tagen

I and Sreeram Kannan had an wonderful opportunity to sit down with Stuart Buck, Executive Director at during Manifest to talk on what has been long-term structural issues with federal funding for science and what are the solutions to fix it. A lot of science that is done outside industrial apparatus (such as in academia) is supposed to geared towards pursuing open-ended science and not just mere hill-climbing. The core issue that we delved into is the paradox that most federal funding that had been allocated via peer review from an expert of panels has the tendency to fund only those proposals that are "safe" and "not risky/speculative." As Stuart points out, this funding style is probably fine with most science but if you look into the history of true scientific breakthroughs, this mechanism wouldn't have approved funding for pursuing that breakthrough by that council of peers. The example that Stuart cited is the chances of funding Einstein when he was patent-office clerk in 1902 to go and explore his out-of-box ideas. Stuart mentioned about alternative mechanisms that are being experimented with programs such as We also touched upon two of the most hotly-debated issues of our time: (1) given that there is increasingly high signal that AI is going to accelerate the iteration time for doing research and help humanity do great science, what should be the role of domain experts? (2) most of AI research and its applications to basic science are hyper-concentrated within frontier labs, what happens to those who are and want to pursue science outside the borders of those labs? Check out the full conversation. 03:18 Einstein in 1902 04:01 the National Institute for Irrelevant Ideas 04:20 Karikó and mRNA 14:37 what everyone knows about NIH grants 16:33 funding the polarizing proposals 17:34 where AI money goes next 24:18 the stack of papers 33:22 finding meaning after AGI

I and Sreeram Kannan had an wonderful opportunity to sit down with Stuart Buck, Executive Director at during Manifest to talk on what has been long-term structural issues with federal funding for science and what are the solutions to fix it. A lot of science that is done outside industrial apparatus (such as in academia) is supposed to geared towards pursuing open-ended science and not just mere hill-climbing. The core issue that we delved into is the paradox that most federal funding that had been allocated via peer review from an expert of panels has the tendency to fund only those proposals that are "safe" and "not risky/speculative." As Stuart points out, this funding style is probably fine with most science but if you look into the history of true scientific breakthroughs, this mechanism wouldn't have approved funding for pursuing that breakthrough by that council of peers. The example that Stuart cited is the chances of funding Einstein when he was patent-office clerk in 1902 to go and explore his out-of-box ideas. Stuart mentioned about alternative mechanisms that are being experimented with programs such as We also touched upon two of the most hotly-debated issues of our time: (1) given that there is increasingly high signal that AI is going to accelerate the iteration time for doing research and help humanity do great science, what should be the role of domain experts? (2) most of AI research and its applications to basic science are hyper-concentrated within frontier labs, what happens to those who are and want to pursue science outside the borders of those labs? Check out the full conversation. 03:18 Einstein in 1902 04:01 the National Institute for Irrelevant Ideas 04:20 Karikó and mRNA 14:37 what everyone knows about NIH grants 16:33 funding the polarizing proposals 17:34 where AI money goes next 24:18 the stack of papers 33:22 finding meaning after AGI

18,204 Aufrufe • vor 28 Tagen

Ethereum is starting from the endgame. Episode 4 of TheCoordinate is a deep dive into Lean Ethereum: a clean-slate rethink of consensus, execution, and data availability. I sat down with Justin Drake from Ethereum Foundation to unpack: > need for the rewrite, > rewrite items: post-quantum security + fast finality, > endgame finality (3-slot -> 2-slot -> maybe 1-slot), > slot anatomy, networking constraints, and the "SOL slots" meme, > real-time ZK proving changing the execution roadmap, > censorship resistance with FOSSIL, > role of L2s in the world of Lean Ethereum, > incentives across proposer, builder, prover, includer, attester. If you’re building on Ethereum or trying to understand where the base layer is headed, this one is for you. This is Episode 4 of TheCoordinate. Hope you enjoy it! ------------------------------- Timestamps: 0:00 Intro: digital intelligence needs digital institutions 0:30 The big questions: Lean Ethereum, consensus/execution, post-quantum 1:25 Why Ethereum needs an endgame mindset (and a clean-slate approach) 3:30 The two “rewrite-class” items: post-quantum security + fast finality 5:52 Beamchain → Lean Consensus → Lean Ethereum (expands beyond consensus) 6:34 ZK EVM + real-time proving within a slot → “10,000 TPS” target 10:10 “SOL slots”: pushing slot duration toward speed-of-light constraints 11:09 3-slot finality (3SF) → endgame finality (2-slot / 1-slot paths) 18:19 eFP2P: erasure-coded gossip, bandwidth efficiency, scaling blobs 26:21 FOSSIL today: inclusion lists + opening includers beyond validators 39:09 Lean VM: minimal ZKVM 51:04 XMSS explained: Merkle signatures, 2^32 leaves, statefulness tradeoff 1:00:36 Rollups: 99.9% throughput on L2s + “native rollups” 1:06:53 Economics: roles (builder/prover/includer/attester), proving costs, stake capping

Ethereum is starting from the endgame. Episode 4 of TheCoordinate is a deep dive into Lean Ethereum: a clean-slate rethink of consensus, execution, and data availability. I sat down with Justin Drake from Ethereum Foundation to unpack: > need for the rewrite, > rewrite items: post-quantum security + fast finality, > endgame finality (3-slot -> 2-slot -> maybe 1-slot), > slot anatomy, networking constraints, and the "SOL slots" meme, > real-time ZK proving changing the execution roadmap, > censorship resistance with FOSSIL, > role of L2s in the world of Lean Ethereum, > incentives across proposer, builder, prover, includer, attester. If you’re building on Ethereum or trying to understand where the base layer is headed, this one is for you. This is Episode 4 of TheCoordinate. Hope you enjoy it! ------------------------------- Timestamps: 0:00 Intro: digital intelligence needs digital institutions 0:30 The big questions: Lean Ethereum, consensus/execution, post-quantum 1:25 Why Ethereum needs an endgame mindset (and a clean-slate approach) 3:30 The two “rewrite-class” items: post-quantum security + fast finality 5:52 Beamchain → Lean Consensus → Lean Ethereum (expands beyond consensus) 6:34 ZK EVM + real-time proving within a slot → “10,000 TPS” target 10:10 “SOL slots”: pushing slot duration toward speed-of-light constraints 11:09 3-slot finality (3SF) → endgame finality (2-slot / 1-slot paths) 18:19 eFP2P: erasure-coded gossip, bandwidth efficiency, scaling blobs 26:21 FOSSIL today: inclusion lists + opening includers beyond validators 39:09 Lean VM: minimal ZKVM 51:04 XMSS explained: Merkle signatures, 2^32 leaves, statefulness tradeoff 1:00:36 Rollups: 99.9% throughput on L2s + “native rollups” 1:06:53 Economics: roles (builder/prover/includer/attester), proving costs, stake capping

86,471 Aufrufe • vor 6 Monaten

Most of CT treats consensus protocols as boring and impenetrable. That’s a mistake. Under the hood, there’s an intense race to design faster, higher-throughput, and adversary-resilient consensus protocols. This work directly determines retail UX and explains why Ethereum, Solana, and other L1s obsess over consensus. For Episode 1 of TheCoordinate, I sat down with Kartik Nayak (Kartik Nayak), one of the world’s leading consensus researchers, to pull consensus out of the black box and build a first-principles mental model: how consensus actually works, how it evolved over 50 years, how today’s sprawling protocol families fit together, and what the next frontier of consensus research looks like. This is Episode 1 of TheCoordinate. Hope you enjoy it.

Most of CT treats consensus protocols as boring and impenetrable. That’s a mistake. Under the hood, there’s an intense race to design faster, higher-throughput, and adversary-resilient consensus protocols. This work directly determines retail UX and explains why Ethereum, Solana, and other L1s obsess over consensus. For Episode 1 of TheCoordinate, I sat down with Kartik Nayak (Kartik Nayak), one of the world’s leading consensus researchers, to pull consensus out of the black box and build a first-principles mental model: how consensus actually works, how it evolved over 50 years, how today’s sprawling protocol families fit together, and what the next frontier of consensus research looks like. This is Episode 1 of TheCoordinate. Hope you enjoy it.

78,608 Aufrufe • vor 7 Monaten

"The only question in post-AGI economics is: what is scarce?" That is Alex Imas (Alex Imas) from Chicago Booth, opening Season 01 of Post AGI. Over an hour we get into why AI "job exposure" misleads everyone, why the robots are coming for physical work before knowledge work, the economy of human-made goods that survives automation, his case against UBI, and whether agents can run an economy better than markets. Full conversation. Moments worth your time: 04:10 Why "AI exposure" doesn't mean what people think 13:35 The robotic "dark warehouses" being built in China 23:20 The case against UBI 45:35 The only question after AGI: what is scarce? Full episode below.

"The only question in post-AGI economics is: what is scarce?" That is Alex Imas (Alex Imas) from Chicago Booth, opening Season 01 of Post AGI. Over an hour we get into why AI "job exposure" misleads everyone, why the robots are coming for physical work before knowledge work, the economy of human-made goods that survives automation, his case against UBI, and whether agents can run an economy better than markets. Full conversation. Moments worth your time: 04:10 Why "AI exposure" doesn't mean what people think 13:35 The robotic "dark warehouses" being built in China 23:20 The case against UBI 45:35 The only question after AGI: what is scarce? Full episode below.

31,379 Aufrufe • vor 2 Monaten

China went from copying Western drugs to being the country America copies, in about ten years. Crémieux came on PostAGI to explain how that happened, and where it leaves open science once AGI is in the picture. We got into where biotech's frontier actually sits right now, why it moved to China, and what happens when AI labs start pulling the whole stack in. Chapters: 1:16 the reproducibility and replicability crisis 7:31 whether AI labs vertically integrate science 14:49 how China became the number one drug innovator 18:53 the pricing trick nobody else figured out 20:51 the law that makes you ask competitors for permission to open a hospital 29:45 what AGI does to all of it

China went from copying Western drugs to being the country America copies, in about ten years. Crémieux came on PostAGI to explain how that happened, and where it leaves open science once AGI is in the picture. We got into where biotech's frontier actually sits right now, why it moved to China, and what happens when AI labs start pulling the whole stack in. Chapters: 1:16 the reproducibility and replicability crisis 7:31 whether AI labs vertically integrate science 14:49 how China became the number one drug innovator 18:53 the pricing trick nobody else figured out 20:51 the law that makes you ask competitors for permission to open a hospital 29:45 what AGI does to all of it

17,694 Aufrufe • vor 2 Monaten

We already have a superintelligence. It's called civilization. Humans, institutions, and now AI agents all interact among each other in one big economy. Allison Duettmann's take is that the real project in such a system is building and preparing AI enabled institutions on top of what already works. Her other argument is that science stayed open for centuries and that has lead to a flourishing outcome for humanity as a whole. Now the frontier models are putting guardrails and restrictions. Open source AI plus community compute ( personally, for me, this definitely resonates with the project Darkbloom) might end up being the only independent path for doing real science outside the labs. 0:25 AI for flourishing, not just fear 4:21 Amateurs vs Google's quantum result 7:06 Decentralized inference on MacBooks 11:58 Civilization as superintelligence 15:38 The case for cryonics Full episode with PostAGI.

We already have a superintelligence. It's called civilization. Humans, institutions, and now AI agents all interact among each other in one big economy. Allison Duettmann's take is that the real project in such a system is building and preparing AI enabled institutions on top of what already works. Her other argument is that science stayed open for centuries and that has lead to a flourishing outcome for humanity as a whole. Now the frontier models are putting guardrails and restrictions. Open source AI plus community compute ( personally, for me, this definitely resonates with the project Darkbloom) might end up being the only independent path for doing real science outside the labs. 0:25 AI for flourishing, not just fear 4:21 Amateurs vs Google's quantum result 7:06 Decentralized inference on MacBooks 11:58 Civilization as superintelligence 15:38 The case for cryonics Full episode with PostAGI.

11,759 Aufrufe • vor 1 Monat

Keine weiteren Inhalte verfügbar