正在加载视频...

视频加载失败

返回首页

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 —...

Marktechpost's profile picture

Marktechpost AI

11,402 subscribers

56,461 次观看 • 4 天前 •via X (Twitter)

科学技术新闻政治教育
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

“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 次观看 • 4 个月前

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 次观看 • 6 个月前

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯
0:53

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯

Xenova

225,128 次观看 • 7 个月前

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 formal verification actually is and the trust boundaries between proof assistants, SMT solvers, and kernels – The full verification stack for RISC-V ZKVMs: from SAIL specs to constraint extraction to soundness proofs – Why writing constraints directly in Lean makes proofs 10–100x more ergonomic – How AI is now proving hard theorems in hours for $200 — and what that unlocks for the whole pipeline They also explore the boundaries problem, why specs can have bugs too, and the end goal of a full Lean stack that bypasses Rust and LLVM entirely. Listen to the full episode ------------------------------------------------------------ TIMECODES: 09:16 – What is formal verification? Proof assistants vs SMT solvers 18:33 – Formal verification of code: specs, semantics, and trust boundaries 29:30 – Formally verifying the Lean Ethereum stack: RISC-V ZKVMs in focus 33:02 – Extracting ZKVM constraints into Lean and proving soundness 36:35 – Writing constraints directly in Lean: 10–100x better proof ergonomics 44:02 – Proving Polishchuk–Spielman in 8 hours for $200 with AI 51:01 – The end goal: a full Lean stack bypassing Rust and LLVM
56:07

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 formal verification actually is and the trust boundaries between proof assistants, SMT solvers, and kernels – The full verification stack for RISC-V ZKVMs: from SAIL specs to constraint extraction to soundness proofs – Why writing constraints directly in Lean makes proofs 10–100x more ergonomic – How AI is now proving hard theorems in hours for $200 — and what that unlocks for the whole pipeline They also explore the boundaries problem, why specs can have bugs too, and the end goal of a full Lean stack that bypasses Rust and LLVM entirely. Listen to the full episode ------------------------------------------------------------ TIMECODES: 09:16 – What is formal verification? Proof assistants vs SMT solvers 18:33 – Formal verification of code: specs, semantics, and trust boundaries 29:30 – Formally verifying the Lean Ethereum stack: RISC-V ZKVMs in focus 33:02 – Extracting ZKVM constraints into Lean and proving soundness 36:35 – Writing constraints directly in Lean: 10–100x better proof ergonomics 44:02 – Proving Polishchuk–Spielman in 8 hours for $200 with AI 51:01 – The end goal: a full Lean stack bypassing Rust and LLVM

Zero Knowledge Podcast

15,143 次观看 • 3 个月前

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:
3:08

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Mckay Wrigley

514,642 次观看 • 3 年前

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.
3:38

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Santiago

230,571 次观看 • 1 年前

Mistral Vibe 2.0 is now available on Le Chat Pro and Team plans. Build, maintain, and ship code faster with the terminal-native coding agent by Mistral AI. Here’s what’s new 🧵
1:18

Mistral Vibe 2.0 is now available on Le Chat Pro and Team plans. Build, maintain, and ship code faster with the terminal-native coding agent by Mistral AI. Here’s what’s new 🧵

Mistral Vibe

391,914 次观看 • 5 个月前

The best programmers don't write code anymore. They write a spec. A test. An eval. T Then they turn the AI on and walk away for hours. It runs. It ships. They review. Evals are the unlock most devs are sleeping on. Here's how top agent teams build them right.
1:25

The best programmers don't write code anymore. They write a spec. A test. An eval. T Then they turn the AI on and walk away for hours. It runs. It ships. They review. Evals are the unlock most devs are sleeping on. Here's how top agent teams build them right.

Rohit

690,904 次观看 • 3 个月前

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own
0:20

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

NO1ennn

40,079 次观看 • 17 天前

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.
0:35

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.

Santiago

79,974 次观看 • 1 年前

SHIPPED. Mistral Vibe is now the AI agent for long-horizon productivity and coding, and the home for Work mode, Code mode, the CLI, and a brand new VS Code extension. Let's go... 🧵
1:59

SHIPPED. Mistral Vibe is now the AI agent for long-horizon productivity and coding, and the home for Work mode, Code mode, the CLI, and a brand new VS Code extension. Let's go... 🧵

Mistral Vibe

232,310 次观看 • 1 个月前

China just dropped a free AI super agent that can build software for you. It’s called DeerFlow 2.0. And it’s exploding on GitHub right now. This thing doesn’t just chat. You give it a goal. - It researches the problem. - Writes the code. - Creates files. - Launches sub-agents. Then delivers a finished result. Basically… an AI dev team in one tool.
0:29

China just dropped a free AI super agent that can build software for you. It’s called DeerFlow 2.0. And it’s exploding on GitHub right now. This thing doesn’t just chat. You give it a goal. - It researches the problem. - Writes the code. - Creates files. - Launches sub-agents. Then delivers a finished result. Basically… an AI dev team in one tool.

Julian Goldie SEO

231,446 次观看 • 4 个月前

How to train a model that actually understands both audio and text like Voxtral from Mistral AI? Here is a quick video walkthrough of the paper.
3:29

How to train a model that actually understands both audio and text like Voxtral from Mistral AI? Here is a quick video walkthrough of the paper.

Sophia Yang, Ph.D.

49,801 次观看 • 11 个月前

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:
1:55

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:

Andrew Ng

387,018 次观看 • 2 年前

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas
3:27

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

119,783 次观看 • 16 天前

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.
1:46

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

Sudo su

27,339 次观看 • 1 个月前

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill
8:28

540,000 lines of Rails is a brutal way to learn the agent era Garry's List shipped with: > 262,000 lines of app code > 276,000 lines of tests > 127 background jobs > 33 cron jobs > a 1,778-line claim verifier Then GStack hit 105k GitHub stars Do not copy the Rails pattern 1. Finish the task with an agent 2. Say `skillify it` 3. Save the markdown skill 4. Keep TypeScript only for deterministic I/O 5. Add a unit test for the code 6. Add an LLM eval for the skill 7. Add an integration test across both 8. Add a resolver so the agent loads the skill next time A Rails feature serves one app A skill pack can run against the next hackathon, repo, customer inbox, research folder, or QA run Audit your repo this week Cut code that only exists to: > re-check model output > retry the same model call > validate what the model already has context for > schedule work because the agent has no reusable procedure > preserve a one-off prompt in chat history Keep the code that touches files, APIs, auth, billing, devices, databases Move the judgment into markdown Test the markdown Reuse the skill

Alpha Batcher

35,693 次观看 • 1 个月前

Honored to join @HF0 for S26 We're building Franklin : an AI agent with its own wallet — it auto-picks the best model for every task and pays per action in USDC. An AI agent that can pay and get paid. 👇
0:24

Honored to join @HF0 for S26 We're building Franklin : an AI agent with its own wallet — it auto-picks the best model for every task and pays per action in USDC. An AI agent that can pay and get paid. 👇

BlockRunAI

17,927 次观看 • 1 个月前

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.
1:29

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.

SCOTTY BEAM

17,209 次观看 • 26 天前

We just released FastA2A! 🎉 On the video, you can see on how to turn a Pydantic AI agent into an A2A server with a single line of code! You can also see how to turn an agent into a CLI chat application. 😁 Check it out on the latest PydanticAI version!
1:16

We just released FastA2A! 🎉 On the video, you can see on how to turn a Pydantic AI agent into an A2A server with a single line of code! You can also see how to turn an agent into a CLI chat application. 😁 Check it out on the latest PydanticAI version!

Pydantic

40,294 次观看 • 1 年前