惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
月光博客
月光博客
aimingoo的专栏
aimingoo的专栏
Google DeepMind News
Google DeepMind News
Recent Announcements
Recent Announcements
MyScale Blog
MyScale Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
S
SegmentFault 最新的问题
Hugging Face - Blog
Hugging Face - Blog
Martin Fowler
Martin Fowler
WordPress大学
WordPress大学
F
Fortinet All Blogs
小众软件
小众软件
D
Docker
U
Unit 42
博客园 - 聂微东
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
IT之家
IT之家
云风的 BLOG
云风的 BLOG
博客园 - 司徒正美
有赞技术团队
有赞技术团队
腾讯CDC

Stack Overflow Blog

The AI magic words From better privacy to our new ChatGPT plugin, here's what's new on Stack Overflow for Agents AI, JD, and other letters of the law AI cybersecurity is a cat and mouse game (Re)introducing Developer Story Java’s age is its AI superpower Scaling your money safely with AI How to build a secure-by-default AI coding agent Elevating security, control, and accessibility: Stack Internal 2026.6 The economics of agent scale: tokens, ROI, and building platforms for AI-first teams (Part 2) The good ol’ days of building Java Inside LinkedIn's cognitive memory agent for agentic personalization Responsible AI adoption needs developer workflow design Dispatches from O'Reilly: The right amount of spec for agentic development Get rid of your CAPTCHA, the future of the web is bots AI Won't Replace Project Managers, But It is Reshaping How Work Gets Done Quantum-Augmented Applications: Integrating Quantum Subroutines into Classical Software Stacks From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) Building an agentic SDLC with a QA engineering mindset What does an agentic SDLC actually look like? No Dumb Questions: What is AI context architecture? Why not just build your own? Solving integration woes with a hackathon Your tokenmaxxing is not valuemaxxing How to be fearlessly AI native Explorers, exploiters, and the myth of the 100x engineer Your MVP doesn’t need a Kubernetes cluster Dispatches from O'Reilly: The best risk mitigation strategy in data? A single source of truth What happens to the internet when robots act like humans? Your trusted knowledge layer: Introducing Stack Internal's new platform experience Developers are attached to tools because tools encode trust
When you keep AI Lean, you keep AI correct
Phoebe Sajor · 2026-08-28 · via Stack Overflow Blog

Blog

Loading…

Ryan chats with Leo de Moura, Senior Principal Applied Scientist at AWS and the creator of the Lean language, about proving correctness in AI agents with the Lean language, how automated reasoning complements probabilistic AI models, and the use of AI for continuous code optimization.

The Stack Overflow Podcast cover art

Lean is a functional programming language and proof assistant that allows developers to write programs and verify their mathematical correctness within the exact same system.

Connect with Leo on LinkedIn and check out his many badges on Stack Overflow.

Congrats to Populist badge winner Peter Lawrey for winning the badge on their answer to Check two float/double values for exact equality.

Add to the discussion

Login with your stackoverflow.com account to take part in the discussion.