Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

How do you actually formally verify the code underpinning Ethereum's future? In this episode (the finale of the lean Ethereum miniseries), Nico sits down with Alex Hicks (Alexander Hicks), lead of Protocol Snarkification at the Ethereum Foundation, to break down formal verification from first principles. They cover: – What...

zeroknowledgefm's profile picture

Zero Knowledge Podcast

22,999 subscribers

15,143 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Leonardo de Moura (Leonardo de Moura) is the creator of Lean and the Z3 theorem prover. I talked with him about how Lean works and why LLMs plus Lean will fundamentally change how we write software and do math. In this episode: • How formal verification and proof assistants work • How Lean will impact handwritten math & software • Lean’s role in recent math breakthroughs • When software is worth formalizing Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:28 How formal verification works 05:21 A new way of writing software 13:15 Proof assistants vs programming languages 21:06 How Lean has assisted in mathematical breakthroughs 32:03 When is it worth formalizing software 33:29 How Lean will impact handwritten math 38:55 The Z3 theorem prover project he started 45:44 The most technically challenging work of his career 51:10 Lean vs its competitors 01:00:37 The future of Lean 01:04:10 Technical book recommendations 01:06:15 Advice for his younger self 01:07:10 Outro
1:08:06

Leonardo de Moura (Leonardo de Moura) is the creator of Lean and the Z3 theorem prover. I talked with him about how Lean works and why LLMs plus Lean will fundamentally change how we write software and do math. In this episode: • How formal verification and proof assistants work • How Lean will impact handwritten math & software • Lean’s role in recent math breakthroughs • When software is worth formalizing Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:28 How formal verification works 05:21 A new way of writing software 13:15 Proof assistants vs programming languages 21:06 How Lean has assisted in mathematical breakthroughs 32:03 When is it worth formalizing software 33:29 How Lean will impact handwritten math 38:55 The Z3 theorem prover project he started 45:44 The most technically challenging work of his career 51:10 Lean vs its competitors 01:00:37 The future of Lean 01:04:10 Technical book recommendations 01:06:15 Advice for his younger self 01:07:10 Outro

Ryan Peterman

13,659 Aufrufe • vor 1 Monat

“Math is code. And code is math.” Carina Hong CEO Axiom on why that idea matters for AI: “For centuries, mathematicians reasoned in natural language. But because of the Curry–Howard correspondence, a proof can also be a program.” “You can translate natural-language math into formal code using systems like Lean. Lean is both a theorem-proving language and a programming language.” “That means you can generate solutions as code and then formally verify them. You can even use the same system to verify programs themselves.” “This creates a flywheel of generation and verification, where AI can both write solutions and prove that they’re correct.”
2:25

“Math is code. And code is math.” Carina Hong CEO Axiom on why that idea matters for AI: “For centuries, mathematicians reasoned in natural language. But because of the Curry–Howard correspondence, a proof can also be a program.” “You can translate natural-language math into formal code using systems like Lean. Lean is both a theorem-proving language and a programming language.” “That means you can generate solutions as code and then formally verify them. You can even use the same system to verify programs themselves.” “This creates a flywheel of generation and verification, where AI can both write solutions and prove that they’re correct.”

Forward Future

24,729 Aufrufe • vor 7 Monaten

Ethereum’s endgame is getting rebuilt, not upgraded. With Lean Consensus (née Beamchain), Ethereum is starting from the endgame: cleaning up technical debt, pushing toward fast finality and preparing for a post-quantum future. It’s one of the most ambitious protocol workstreams for Ethereum and for crypto infrastructure overall. I had a conversation with Justin Drake to understand what Lean Ethereum really is in terms of: real-time proving, the path to higher L1 throughput and what it unlocks for rollups. Stay tuned for the full episode of TheCoordinate podcast!
0:34

Ethereum’s endgame is getting rebuilt, not upgraded. With Lean Consensus (née Beamchain), Ethereum is starting from the endgame: cleaning up technical debt, pushing toward fast finality and preparing for a post-quantum future. It’s one of the most ambitious protocol workstreams for Ethereum and for crypto infrastructure overall. I had a conversation with Justin Drake to understand what Lean Ethereum really is in terms of: real-time proving, the path to higher L1 throughput and what it unlocks for rollups. Stay tuned for the full episode of TheCoordinate podcast!

Soubhik Deb

23,332 Aufrufe • vor 6 Monaten

Axiom Math's Carina Hong on why verification isn't about catching mistakes, it's how you drive the cost of a proof to zero: "Formal verification is going to make your life slightly better if you're facing a proof with one million lines. Remember the Erdős unit distance problem, the chain of thought being generated? There are actual mathematicians trying to follow it step by step and scrutinize it. That seems very difficult if you're not in that very niche domain of discrete geometry intersecting with algebraic number theory." "But if you have a Lean proof accompanying it, you can just run it. And running the Lean proof gives you that provable guarantee that this proof is sound." "I have a hot take. People think Lean is this library built on the existing Mathlib. I think it's going to grow significantly. A lot of the hurdles where Lean is difficult is that the basic definitions of some mathematical fields are just not in the library." "My hot take is the scaling law, if you go down the formal mathematics path, is going to be a lot steeper than informal mathematics. So it's not just for verification, for trust, it's also for performance, it's also for optimal generation." "Verification is not like insurance. It's not something where, oh, we want to make sure there's no flaw. That's great, but it also helps you generate mathematics, both proofs and conjectures and theories, a lot better." "So imagine the cost of proof goes to zero. Then you can massage the problem statements, and even if it's an open problem, a lot more easily, flexibly, and adaptively." Carina Hong Axiom
3:17

Axiom Math's Carina Hong on why verification isn't about catching mistakes, it's how you drive the cost of a proof to zero: "Formal verification is going to make your life slightly better if you're facing a proof with one million lines. Remember the Erdős unit distance problem, the chain of thought being generated? There are actual mathematicians trying to follow it step by step and scrutinize it. That seems very difficult if you're not in that very niche domain of discrete geometry intersecting with algebraic number theory." "But if you have a Lean proof accompanying it, you can just run it. And running the Lean proof gives you that provable guarantee that this proof is sound." "I have a hot take. People think Lean is this library built on the existing Mathlib. I think it's going to grow significantly. A lot of the hurdles where Lean is difficult is that the basic definitions of some mathematical fields are just not in the library." "My hot take is the scaling law, if you go down the formal mathematics path, is going to be a lot steeper than informal mathematics. So it's not just for verification, for trust, it's also for performance, it's also for optimal generation." "Verification is not like insurance. It's not something where, oh, we want to make sure there's no flaw. That's great, but it also helps you generate mathematics, both proofs and conjectures and theories, a lot better." "So imagine the cost of proof goes to zero. Then you can massage the problem statements, and even if it's an open problem, a lot more easily, flexibly, and adaptively." Carina Hong Axiom

MTS

13,273 Aufrufe • vor 1 Monat

“What if the most important AI infrastructure isn’t the biggest model — but the one you can actually trust?” Sachi Miyasaki sits down with Karan Sirdesai Karan, Founder of Mira, to explore how Mira is approaching decentralized AI from a more focused angle: making machine intelligence reliable enough for real-world use. They discuss why Mira is not trying to become a full-stack AI protocol, how its approach differs from networks like Bittensor, Ritual, and Sahara, and why focusing on trust and verification could make Mira a stronger fit inside the wider AI infrastructure stack. The episode also breaks down Mira’s reliability architecture, from its core verification layer to node-level consensus, and why the next evolution of AI APIs may not be about simply accessing more models, but about knowing whether the answers you receive can actually be trusted.
2:22

“What if the most important AI infrastructure isn’t the biggest model — but the one you can actually trust?” Sachi Miyasaki sits down with Karan Sirdesai Karan, Founder of Mira, to explore how Mira is approaching decentralized AI from a more focused angle: making machine intelligence reliable enough for real-world use. They discuss why Mira is not trying to become a full-stack AI protocol, how its approach differs from networks like Bittensor, Ritual, and Sahara, and why focusing on trust and verification could make Mira a stronger fit inside the wider AI infrastructure stack. The episode also breaks down Mira’s reliability architecture, from its core verification layer to node-level consensus, and why the next evolution of AI APIs may not be about simply accessing more models, but about knowing whether the answers you receive can actually be trusted.

BeaconLayer

79,152 Aufrufe • vor 1 Monat

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: And see the complete proof on GitHub:
0:34

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: And see the complete proof on GitHub:

Anthropic

4,532,556 Aufrufe • vor 5 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
1:16:31

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

Soubhik Deb

86,471 Aufrufe • vor 6 Monaten

Xavier Leroy (creator of OCaml) is an expert in compilers, formal verification of software and functional programming. This interview should be an approachable resource if you're curious about formal verification of software since I was learning that on the fly during it. In this episode: • OCaml compared with Rust and JavaScript • What is formal verification and how does it work • How languages call each other across boundaries • How to address "almost-correct" LLM code • How type inference works in programming languages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 - Intro 00:43 - What sets OCaml apart 04:39 - OCaml vs Rust 07:57 - Why is manual memory management more performant 11:21 - Javascript vs OCaml 14:00 - Famous Rob Pike quote 16:05 - Type inference and how it works 22:12 - What is formal verification and how does it work 40:07 - What made multicore support difficult for OCaml 50:17 - How programming languages interface and call each other 57:41 - The danger of almost-correct LLM code 01:05:39 - How LLMs will change programming languages 01:10:26 - Industry vs academia 01:15:05 - Most interesting unsolved problems 01:18:30 - Top book recommendations for engineers 01:21:17 - Advice for his younger self 01:23:31 - Outro
1:24:27

Xavier Leroy (creator of OCaml) is an expert in compilers, formal verification of software and functional programming. This interview should be an approachable resource if you're curious about formal verification of software since I was learning that on the fly during it. In this episode: • OCaml compared with Rust and JavaScript • What is formal verification and how does it work • How languages call each other across boundaries • How to address "almost-correct" LLM code • How type inference works in programming languages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 - Intro 00:43 - What sets OCaml apart 04:39 - OCaml vs Rust 07:57 - Why is manual memory management more performant 11:21 - Javascript vs OCaml 14:00 - Famous Rob Pike quote 16:05 - Type inference and how it works 22:12 - What is formal verification and how does it work 40:07 - What made multicore support difficult for OCaml 50:17 - How programming languages interface and call each other 57:41 - The danger of almost-correct LLM code 01:05:39 - How LLMs will change programming languages 01:10:26 - Industry vs academia 01:15:05 - Most interesting unsolved problems 01:18:30 - Top book recommendations for engineers 01:21:17 - Advice for his younger self 01:23:31 - Outro

Ryan Peterman

23,942 Aufrufe • vor 1 Monat

There’s a popular theory that AI will finally make formal verification mainstream because mathematical proof of correctness will be needed when machines write most or all of the code. But will this happen? Hillel Wayne is one of the best people to answer. Timestamps: 00:00 Intro 04:32 The Crossover Project 11:37 What software engineering does better 15:30 What traditional engineering does better 18:17 Formal methods 29:32 TLA+: what it is and demo 36:58 TLA+ at Amazon 38:10 Ways distributed systems break 41:03 Formal methods and systems thinking 46:20 The value of learning math 50:23 What TLA+ is good for and isn’t 52:50 Alloy: a declarative language for software modeling 58:53 Other formal methods tools 1:01:24 Property-based testing 1:05:31 AI and the need for formal verification 1:12:29 Logic for programmers 1:14:35 Hillel’s 2025 prediction on AI’s impact 1:21:30 Book recommendation Brought to you by: • Antithesis – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages. • turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. • WorkOS – everything you need to make your app enterprise ready. Two things I found especially interesting, talking with Hillel: 1. Amazon used TLA+ to find a bug almost impossible to locate without formal methods. In the paper How AWS uses formal methods, the AWS team shared that they’d found a complicated bug for which the shortest error trace to exhibit was 35 steps (!!). The bug passed unnoticed through extensive design review, code reviews, and testing. AWS concluded they wouldn’t have uncovered it if they’d stuck to conventional testing approaches. 2. Why not use formal verification for everything, then? It’s because specs in the real world are a nightmare to write. Even a simple problem like “find the file in a directory that has the most lines” gets complicated when modeled with formal methods. We would have to answer questions like: ‘do we look at ASCII or UTF-8 new line characters, what about unreadable files, and Symlinks?’ Without formal methods, we can write a simple verification that is right in 99%+ of cases. Formal methods require a lot of extra effort for the less than 1% of exotic use cases!
1:24:52

There’s a popular theory that AI will finally make formal verification mainstream because mathematical proof of correctness will be needed when machines write most or all of the code. But will this happen? Hillel Wayne is one of the best people to answer. Timestamps: 00:00 Intro 04:32 The Crossover Project 11:37 What software engineering does better 15:30 What traditional engineering does better 18:17 Formal methods 29:32 TLA+: what it is and demo 36:58 TLA+ at Amazon 38:10 Ways distributed systems break 41:03 Formal methods and systems thinking 46:20 The value of learning math 50:23 What TLA+ is good for and isn’t 52:50 Alloy: a declarative language for software modeling 58:53 Other formal methods tools 1:01:24 Property-based testing 1:05:31 AI and the need for formal verification 1:12:29 Logic for programmers 1:14:35 Hillel’s 2025 prediction on AI’s impact 1:21:30 Book recommendation Brought to you by: • Antithesis – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages. • turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. • WorkOS – everything you need to make your app enterprise ready. Two things I found especially interesting, talking with Hillel: 1. Amazon used TLA+ to find a bug almost impossible to locate without formal methods. In the paper How AWS uses formal methods, the AWS team shared that they’d found a complicated bug for which the shortest error trace to exhibit was 35 steps (!!). The bug passed unnoticed through extensive design review, code reviews, and testing. AWS concluded they wouldn’t have uncovered it if they’d stuck to conventional testing approaches. 2. Why not use formal verification for everything, then? It’s because specs in the real world are a nightmare to write. Even a simple problem like “find the file in a directory that has the most lines” gets complicated when modeled with formal methods. We would have to answer questions like: ‘do we look at ASCII or UTF-8 new line characters, what about unreadable files, and Symlinks?’ Without formal methods, we can write a simple verification that is right in 99%+ of cases. Formal methods require a lot of extra effort for the less than 1% of exotic use cases!

Gergely Orosz

34,678 Aufrufe • vor 1 Monat

How will autonomous AI agents shape the future of Ethereum? In Episode 20 of the Agents Unleashed podcast, maybrier ☴ talks with Tomasz K. Stańczak, Co-Executive Director of the Ethereum Foundation, about Ethereum’s next decade and the rise of agentic AI, both on and off-chain. In this episode: • Strategic priorities for Ethereum’s next upgrades • Why cypherpunk values like privacy + decentralization still matter • How AI agents could use Ethereum as their coordination + verification layer • What “identity is defined by privacy” really means in an AI world 02:05 – Tomasz on his role at Ethereum Foundation 04:21 – What about Ethereum’s mission resonated with him 06:48 – The Foundation's strategic priorities for AI 10:09 – Keeping cypherpunk values alive 15:34 – The next 10 years: AI, robotics, and blockchain 20:55 – Identity, privacy, and AI agents 26:30 – Predictions for the future of the AI user interface 31:36 – Call to action for builders This episode is sponsored by Sigil Fund
33:46

How will autonomous AI agents shape the future of Ethereum? In Episode 20 of the Agents Unleashed podcast, maybrier ☴ talks with Tomasz K. Stańczak, Co-Executive Director of the Ethereum Foundation, about Ethereum’s next decade and the rise of agentic AI, both on and off-chain. In this episode: • Strategic priorities for Ethereum’s next upgrades • Why cypherpunk values like privacy + decentralization still matter • How AI agents could use Ethereum as their coordination + verification layer • What “identity is defined by privacy” really means in an AI world 02:05 – Tomasz on his role at Ethereum Foundation 04:21 – What about Ethereum’s mission resonated with him 06:48 – The Foundation's strategic priorities for AI 10:09 – Keeping cypherpunk values alive 15:34 – The next 10 years: AI, robotics, and blockchain 20:55 – Identity, privacy, and AI agents 26:30 – Predictions for the future of the AI user interface 31:36 – Call to action for builders This episode is sponsored by Sigil Fund

Olas (formerly Autonolas)

17,462 Aufrufe • vor 1 Jahr

Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems Most AI theorem proving is a language model generating a proof in one shot, with a verifier bolted on at the end to check it. That's autocomplete with a grader — and Mistral just drew a clear line between that and an actual proof agent. They released Leanstral 1.5 — a 119B MoE with 6.5B active parameters, trained as a code agent that lives inside the Lean 4 compiler loop: propose a proof, read the compiler's goals and errors, refine, repeat until it compiles or the budget runs out. Verification isn't the eval here. It's the training signal. Here's what's actually interesting: → Test-time scaling behaves like a dial: PutnamBench Pass@8 climbs 44 → 244 → 493 → 587 solved as the per-attempt token budget moves 50k → 200k → 1M → 4M → 587/672 on PutnamBench at ~$4 per problem, versus an estimated $300+ for Seed-Prover 1.5 high (a 10 H20-days-per-problem budget) → Saturates miniF2F: 100% on both validation and test sets → Two RL environments in training — a multiturn prover, and a raw-filesystem code agent that edits files, runs bash, and queries the Lean language server for live goals and types → Not just math: an Aeneas (Rust → Lean) pipeline flagged 11 genuine bugs across 57 repos, 5 previously unreported — including an integer overflow in datrs/varinteger when (value + 1) hits Std.U64.MAX Apache 2.0 weights, free API endpoint Full analysis: Model weights: Project: Technical Details: Mistral AI Mistral AI for Developers Sophia Yang, Ph.D.
0:25

Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems Most AI theorem proving is a language model generating a proof in one shot, with a verifier bolted on at the end to check it. That's autocomplete with a grader — and Mistral just drew a clear line between that and an actual proof agent. They released Leanstral 1.5 — a 119B MoE with 6.5B active parameters, trained as a code agent that lives inside the Lean 4 compiler loop: propose a proof, read the compiler's goals and errors, refine, repeat until it compiles or the budget runs out. Verification isn't the eval here. It's the training signal. Here's what's actually interesting: → Test-time scaling behaves like a dial: PutnamBench Pass@8 climbs 44 → 244 → 493 → 587 solved as the per-attempt token budget moves 50k → 200k → 1M → 4M → 587/672 on PutnamBench at ~$4 per problem, versus an estimated $300+ for Seed-Prover 1.5 high (a 10 H20-days-per-problem budget) → Saturates miniF2F: 100% on both validation and test sets → Two RL environments in training — a multiturn prover, and a raw-filesystem code agent that edits files, runs bash, and queries the Lean language server for live goals and types → Not just math: an Aeneas (Rust → Lean) pipeline flagged 11 genuine bugs across 57 repos, 5 previously unreported — including an integer overflow in datrs/varinteger when (value + 1) hits Std.U64.MAX Apache 2.0 weights, free API endpoint Full analysis: Model weights: Project: Technical Details: Mistral AI Mistral AI for Developers Sophia Yang, Ph.D.

Marktechpost AI

56,695 Aufrufe • vor 2 Monaten

Vitalik Buterin is prioritizing Quantum resistance for Ethereum vitalik.eth has unveiled the 2026 "Strawmap," detailing a structural shift in Ethereum's development to counter emerging cryptographic and scaling challenges. The updated architecture elevates quantum safety to a primary priority by introducing LeanSPHINCS signatures and "zkzk frames" to facilitate native rollups. This transition marks a pivot away from the traditional EVM toward more efficient, AI-verifiable ISAs such as RISC-V, to maintain a "Lean" protocol core that can be formally verified at scale.
0:30

Vitalik Buterin is prioritizing Quantum resistance for Ethereum vitalik.eth has unveiled the 2026 "Strawmap," detailing a structural shift in Ethereum's development to counter emerging cryptographic and scaling challenges. The updated architecture elevates quantum safety to a primary priority by introducing LeanSPHINCS signatures and "zkzk frames" to facilitate native rollups. This transition marks a pivot away from the traditional EVM toward more efficient, AI-verifiable ISAs such as RISC-V, to maintain a "Lean" protocol core that can be formally verified at scale.

BSCN

18,866 Aufrufe • vor 1 Monat

We've been working with Kev and ladislaus.eth from Ethereum Foundation and donnoh.gwei 💗 from L2BEAT 💗 on a proof of concept of EIP-8079 (native rollups) using ethrex. Native rollups reuse Ethereum's own execution to verify L2 state transitions. No ZK circuits, no fraud proofs, no complex proof systems to maintain. Every L1 upgrade is automatically inherited. Any bug in the verification is also a bug in Ethereum itself. The demo shows a full end-to-end native rollup: - L2 blocks settled to L1 via the EXECUTE precompile - L1→L2 deposit - Contract deployment and cross-layer calls - L2→L1 withdrawal with MPT proof claim - Blockscout verifying EXECUTE precompile calls on L1 Try it yourself. Instructions in the PR below.
2:12

We've been working with Kev and ladislaus.eth from Ethereum Foundation and donnoh.gwei 💗 from L2BEAT 💗 on a proof of concept of EIP-8079 (native rollups) using ethrex. Native rollups reuse Ethereum's own execution to verify L2 state transitions. No ZK circuits, no fraud proofs, no complex proof systems to maintain. Every L1 upgrade is automatically inherited. Any bug in the verification is also a bug in Ethereum itself. The demo shows a full end-to-end native rollup: - L2 blocks settled to L1 via the EXECUTE precompile - L1→L2 deposit - Contract deployment and cross-layer calls - L2→L1 withdrawal with MPT proof claim - Blockscout verifying EXECUTE precompile calls on L1 Try it yourself. Instructions in the PR below.

ethrex

26,907 Aufrufe • vor 6 Monaten

It's finally here - the Official Lean AI Company Playbook 1000+ founders, investors and execs have been flooding my DMs about. Ever since I created the Official Lean AI Leaderboard after exiting my $150M annual revenue startup, founders from across the globe have asked me this one question: "How are these lean AI companies generating millions with tiny teams?" So I spent the last 3 months obsessively tracking and collaborating with 30+ lean AI-native founders, researching the answer. Here's what I discovered: They've built operational systems that multiply human capability. Instead of scaling headcount, they've created AI-powered processes that let small teams operate at unprecedented scale. And their secret goes far beyond the specific AI tools they use. It lies in redesigning their entire company operations around a fundamentally different approach to growth and execution. After countless conversations, interviews, and behind-the-scenes exclusive access, I finally documented the exact playbook with complete systems. This comprehensive playbook includes: • A complete breakdown of the tech stack and operational workflows • The organizational design principles that enable tiny teams to do massive work • Critical inflection points where things break (and how to navigate them) • A detailed 6-month implementation plan for starting your own lean AI company (with weekly actions) • Implementation best practices from dozens of successful lean AI-native companies Want the ultimate Lean AI Playbook or help transforming your Lean AI operations? 👇 • Like and Share this post • Comment "Lean AI Playbook" • Follow me (so I can DM you) --------------- PS: Separately, I'm opening a limited number of high-impact advising slots for serious founders and operators who want to work directly with me—beyond just consuming my content. If you're ready to transform how your company operates using AI, DM me. (Please note: these are paid spots due to limited availability and time atm)
0:48

It's finally here - the Official Lean AI Company Playbook 1000+ founders, investors and execs have been flooding my DMs about. Ever since I created the Official Lean AI Leaderboard after exiting my $150M annual revenue startup, founders from across the globe have asked me this one question: "How are these lean AI companies generating millions with tiny teams?" So I spent the last 3 months obsessively tracking and collaborating with 30+ lean AI-native founders, researching the answer. Here's what I discovered: They've built operational systems that multiply human capability. Instead of scaling headcount, they've created AI-powered processes that let small teams operate at unprecedented scale. And their secret goes far beyond the specific AI tools they use. It lies in redesigning their entire company operations around a fundamentally different approach to growth and execution. After countless conversations, interviews, and behind-the-scenes exclusive access, I finally documented the exact playbook with complete systems. This comprehensive playbook includes: • A complete breakdown of the tech stack and operational workflows • The organizational design principles that enable tiny teams to do massive work • Critical inflection points where things break (and how to navigate them) • A detailed 6-month implementation plan for starting your own lean AI company (with weekly actions) • Implementation best practices from dozens of successful lean AI-native companies Want the ultimate Lean AI Playbook or help transforming your Lean AI operations? 👇 • Like and Share this post • Comment "Lean AI Playbook" • Follow me (so I can DM you) --------------- PS: Separately, I'm opening a limited number of high-impact advising slots for serious founders and operators who want to work directly with me—beyond just consuming my content. If you're ready to transform how your company operates using AI, DM me. (Please note: these are paid spots due to limited availability and time atm)

Henry Shi

121,697 Aufrufe • vor 1 Jahr

In this episode of the Lightcone Podcast, we sat down with Mukund Jha and Madhav Jha, the founders of Emergent - an AI platform that lets anyone build and ship production-ready software. In just eight months, users have created more than 7 million apps on Emergent, with the number doubling in just the last 45 days. We discuss how they built one of the most powerful AI coding agents, why they focused on non-technical users and what it's like building for a global audience from India. 00:00 - Intro 01:06 - What Is Emergent? 01:18 - Founder Backstory 02:09 - From AI Testing to General Coding Agents 02:52 - Getting Ahead of the Market 04:18 - The Pivot to Non-Technical Users 05:22 - Why Second Movers Can Win in AI 09:04 - Building for Production, Not Just Prototypes 18:21 - Live Demo: Building Apps with Emergent 24:40 - How Emergent Hires and Runs a Lean Team 29:04 - Is SaaS Dead? The Rise of Personalized Software 34:04 - The Future: Niche Apps, Solo Builders and AI Agency
39:32

In this episode of the Lightcone Podcast, we sat down with Mukund Jha and Madhav Jha, the founders of Emergent - an AI platform that lets anyone build and ship production-ready software. In just eight months, users have created more than 7 million apps on Emergent, with the number doubling in just the last 45 days. We discuss how they built one of the most powerful AI coding agents, why they focused on non-technical users and what it's like building for a global audience from India. 00:00 - Intro 01:06 - What Is Emergent? 01:18 - Founder Backstory 02:09 - From AI Testing to General Coding Agents 02:52 - Getting Ahead of the Market 04:18 - The Pivot to Non-Technical Users 05:22 - Why Second Movers Can Win in AI 09:04 - Building for Production, Not Just Prototypes 18:21 - Live Demo: Building Apps with Emergent 24:40 - How Emergent Hires and Runs a Lean Team 29:04 - Is SaaS Dead? The Rise of Personalized Software 34:04 - The Future: Niche Apps, Solo Builders and AI Agency

Y Combinator

107,800 Aufrufe • vor 5 Monaten

House of ZK is proud to announce the full sponsor lineup for Verifying Intelligence 3.0 - Where ZK Meets AI & x402 - at Ethereum Devcon, Argentina 🇦🇷 Supported by leading builders across the ZK & AI spaces - Starknet (BTCFi arc) 🥷, Mina Protocol (httpz) 🪶, ZKM, zk V e r i f y, 0G Labs (Home of Infinite AI), Ontology - The Trust Layer for Web3, Veridise, and Ethereum Argentina 🦇🔊 - this edition brings together the projects defining the infrastructure for verifiable compute, decentralized intelligence, and the trustless Internet. Taking place on November 19th at Cultural Vivo, Verifying Intelligence will explore the verification stack for agentic AI: proof-carrying inference, private data pipelines, provenance, and verifiable micropayments via x402. If you’re in Buenos Aires for DevConnect, this is the one event you don’t want to miss. RSVP now:
0:43

House of ZK is proud to announce the full sponsor lineup for Verifying Intelligence 3.0 - Where ZK Meets AI & x402 - at Ethereum Devcon, Argentina 🇦🇷 Supported by leading builders across the ZK & AI spaces - Starknet (BTCFi arc) 🥷, Mina Protocol (httpz) 🪶, ZKM, zk V e r i f y, 0G Labs (Home of Infinite AI), Ontology - The Trust Layer for Web3, Veridise, and Ethereum Argentina 🦇🔊 - this edition brings together the projects defining the infrastructure for verifiable compute, decentralized intelligence, and the trustless Internet. Taking place on November 19th at Cultural Vivo, Verifying Intelligence will explore the verification stack for agentic AI: proof-carrying inference, private data pipelines, provenance, and verifiable micropayments via x402. If you’re in Buenos Aires for DevConnect, this is the one event you don’t want to miss. RSVP now:

House of ZK

22,991 Aufrufe • vor 10 Monaten

Since 2020, CoinFund’s investment thesis in World has been driven by the idea that biometric proof of personhood is critical for identity verification. Amid today’s rapid expansion of AI, it’s becoming an increasingly important problem to solve. Alex Blania, CEO of Tools for Humanity – the company behind World (formerly Worldcoin) – sat down with CoinFund CEO Jake Brukhman to discuss the company’s approach to proof of personhood, its emerging ecosystem of projects, and why identity verification is urgent to address. They discuss: - From Worldcoin to World (2:45) - Building on World Chain (7:36) - Distributing identity (24:08) - Why proof of personhood (28:55) - The underlying rails for adoption (41:58) Tune into the latest episode of Mined with CoinFund, available on Apple, Spotify, and YouTube.
0:48

Since 2020, CoinFund’s investment thesis in World has been driven by the idea that biometric proof of personhood is critical for identity verification. Amid today’s rapid expansion of AI, it’s becoming an increasingly important problem to solve. Alex Blania, CEO of Tools for Humanity – the company behind World (formerly Worldcoin) – sat down with CoinFund CEO Jake Brukhman to discuss the company’s approach to proof of personhood, its emerging ecosystem of projects, and why identity verification is urgent to address. They discuss: - From Worldcoin to World (2:45) - Building on World Chain (7:36) - Distributing identity (24:08) - Why proof of personhood (28:55) - The underlying rails for adoption (41:58) Tune into the latest episode of Mined with CoinFund, available on Apple, Spotify, and YouTube.

CoinFund

13,408 Aufrufe • vor 1 Jahr

“You’ve just been told you have superpowers.” AI agents are starting to feel like coworkers. The cost of automation is collapsing. So what happens to jobs? To startups? To crypto? We break down the new paper “Some Simple Economics of AGI” with coauthor Christian Catalini, including: • Why verification becomes the bottleneck • Practical advice for early- and late-career builders • The risk of a hollow economy, and the path to an augmented one • Why crypto may be essential infrastructure for identity, provenance, and trust In conversation with Eddy Lazzarin ☀️ and Robert Hackett. Full episode ↓
1:05:40

“You’ve just been told you have superpowers.” AI agents are starting to feel like coworkers. The cost of automation is collapsing. So what happens to jobs? To startups? To crypto? We break down the new paper “Some Simple Economics of AGI” with coauthor Christian Catalini, including: • Why verification becomes the bottleneck • Practical advice for early- and late-career builders • The risk of a hollow economy, and the path to an augmented one • Why crypto may be essential infrastructure for identity, provenance, and trust In conversation with Eddy Lazzarin ☀️ and Robert Hackett. Full episode ↓

a16z crypto

205,807 Aufrufe • vor 6 Monaten

Jolt Pro is a 100x improvement over existing zkVMs. After months of researching all existing zkVMs, we realized none of them could scale to what we needed with Zero. Then we came across Justin Thaler's work and Jolt, a research project from a16z crypto. We saw massive potential in the math and, finally, a viable way to scale to our needs. So we secretly assembled a team of some of the brightest minds across cryptography, GPU programming, and ASIC design to build an internal Jolt Pro team. Jolt Pro has no precompiles; it runs only RISC-V instructions, without introducing new ad hoc, error-prone constraints. It's impossible to compare against other zkVMs because they are not proving straight RISC-V, most of their work and speed gains exist in dangerous pre-compiles. Jolt Pro scales to infinity. The number of cells you can use in parallel is only limited by the size of the datacenter. Jolt Pro has a path to 4GHz cells using the same configuration we use for our 1.61 GHz cell today. By early 2027, it will be post-quantum and set the standard for all zkVMs. We will eventually make "zero-proofs", and others can try to beat our RISC-V proving in the open. For now, we stay heads down, building Zero to be everything the industry ever wanted. And then just a little more.
2:18

Jolt Pro is a 100x improvement over existing zkVMs. After months of researching all existing zkVMs, we realized none of them could scale to what we needed with Zero. Then we came across Justin Thaler's work and Jolt, a research project from a16z crypto. We saw massive potential in the math and, finally, a viable way to scale to our needs. So we secretly assembled a team of some of the brightest minds across cryptography, GPU programming, and ASIC design to build an internal Jolt Pro team. Jolt Pro has no precompiles; it runs only RISC-V instructions, without introducing new ad hoc, error-prone constraints. It's impossible to compare against other zkVMs because they are not proving straight RISC-V, most of their work and speed gains exist in dangerous pre-compiles. Jolt Pro scales to infinity. The number of cells you can use in parallel is only limited by the size of the datacenter. Jolt Pro has a path to 4GHz cells using the same configuration we use for our 1.61 GHz cell today. By early 2027, it will be post-quantum and set the standard for all zkVMs. We will eventually make "zero-proofs", and others can try to beat our RISC-V proving in the open. For now, we stay heads down, building Zero to be everything the industry ever wanted. And then just a little more.

LayerZero

29,409 Aufrufe • vor 6 Monaten