🌹 Today we're releasing Unifloral, our new library for Offline Reinforcement Learning! We make research easy: ⚛️ Single-file 🤏 Minimal ⚡️ End-to-end Jax Best of all, we unify prior methods into one algorithm - a single hyperparameter space for research! ⤵️

Extremely useful repo: github.com/sirosen/textho…

Half the world’s code is below average!!!!

It's time to think about code generation beyond functional correctness. Refactoring multiple libraries requires designing APIs that support past and future use cases, which is challenging for even human engineers. Can't wait for LLMs to unify pytorch, tensorflow, and jax 😬

Super excited to share my new work! The goal? Moving code agents beyond functional correctness to software design*. We present Librarian, a refactoring method, and MiniCode, a verifiable benchmark for agents to create general, reusable libraries by minimizing code across repos!

ziga is amazing, hire him x.com/zzigakovacic/s…

We now know RL agents can zero-shot crush driving benchmarks. Can we put them on a car and replace the planning stack? We're hiring a postdoc at NYU to find out! Email me if interested and please help us get the word out.

First step towards reducing slop

awesome work and clear writeup. every agent runtime will need to branch and snapshot. the "open questions" at the end of this post have been solved at Morph for a while with Infinibranch and are generally available for agent developers everywhere: cloud.morph.so

[1/5] We have a quick update to share, which contradicts our hypothesis regarding the abilities of Muon and Adam vis-a-vis Grokking.

Introducing Warp 2.0: the Agentic Development Environment 1️⃣ Top overall coding agent: #1 on Terminal-Bench, 71% on SWE-bench Verified 2️⃣ Agent multi-threading: build features, debug, and ship all at once 3️⃣ The first all-in-one platform for agentic development 🧵 Learn more