You can now connect your Letta Code agent to GitHub with the command /install-github-app ! 👾 Since agents are stateful, you can interact with the same agent with the same persistent memory on GitHub and locally in your CLI.

Leslie Lamport won a Turing award for his fundamental contributions to distributed systems. For instance, he invented the Paxos consensus algorithm that is a critical component of many distributed systems today. I interviewed him about his work and career. We discussed: • Why

I want to share a little story for my own research life that I cut from the essay I posted this weekend, but which I think gives an interesting look into where AI tools are currently for day-to-day research tasks. For a project I am working on now, I and my two coauthors needed

Some thoughts on AI and mathematics, inspired by "First Proof."

You can understand more about how learning works from Ravi Vakils page for PhD students than 90% of writing on this topic

Updates: Excited to share that Agent Data Protocol (ADP) is accepted to ICLR 2026 Oral! 🎉 We also added support for 3 new datasets: SWE-Play, MiniCoder, and Toucan, bringing us to 3M trajectories supported. If you're training agentic LMs, try ADP + tell us what dataset/agent

🔥 We’re partnering with researchers to push the frontier of mathematics and science using AI. If you want to build the future with us, take a look: https://t.co/TmCdEBxIPY

We're releasing Letta Code, a memory-first coding agent - open source (apache 2.0) - model agnostic - portable agent learning and memory

‼️Position: AI coding agent research needs recalibration. We've heavily optimized for solo autonomy, and far less for designing agents that empower the humans using them. It’s time to build human-centered coding agents. 🧵

Talk slides now available if interested: https://t.co/60HEVmnBUI

Recently I gave a talk on LLMs for Math Research (mostly to an audience of pure and applied mathematicians) I tried to compile the latest progress in one presentation pdf and video recording: https://t.co/Q5qvnEwAiE

Beautiful talk by Barry Mazur on the BSD conjecture from a few days ago here: https://t.co/3NV1KYpHXn Good example of a quite early major impact of computing on mathematics research.

This paper describes our Aletheia system that solved multiple open Erdős problems. It also contributed intermediate propositions on two research papers, collaborated with a human author on a third paper, and produced a standalone fourth paper on its own. https://t.co/lHOtzrJ1kv

Our blog post describes how Deep Think agents are making research progress in pure mathematics, physics, and computer science. https://t.co/QAi9aagb5E

We are looking for brilliant deep learning researchers to help us solve program synthesis at @ndea. If you strongly feel like AGI should be capable of invention, not just automation, consider joining us. Apply here:

Formed this team 4 weeks ago. We’ve had a good start to 2026, and we're having a ton of fun with some early results. We’re scaling up. Lean experts... join us at @axiommathai we’re hiring. Please share... 📧 careers@axiommath.ai @leanprover

Takeaway: formalization isn't just about rigor — it forces you to confront every implicit assumption textbooks silently skip. The future is the mixture of natural language and Lean for ai4math.

🚀 We present the first large-scale Lean 4 formulation of Statistical learning theory from scratch! Led by my student @yuanhezhang6 and collaborated with @jasondeanlee 📄 Paper: https://t.co/8q5laY8KYp 💻 GitHub: https://t.co/mTpkr92TMQ 🤗 Dataset: https://t.co/K8wDD6us4k

CSLib: The Lean computer science library. ~ Clark Barrett, Swarat Chaudhuri, Fabrizio Montesi, Jim Grundy, Pushmeet Kohli, Leonardo de Moura, Alexandre Rademaker, Sorrachai Yingchareonthawornchai. https://t.co/5aruq4Nl3S #ITP #LeanProver #CompSci

Five reasons I do AI for math: We’re entering an era of instant access to domain-expert skills coupled with Lean-verification. We can now turn human curiosity into assisted intuition, and then into certified truth. 🧵 @axiommathai @leanprover