DeepSeek V3.1 beats Claude 4 Opus on Aider Polyglot This makes it the best non-TTC coding model and all of that for ~$1

Claim: gpt-5-pro can prove new interesting mathematics. Proof: I took a convex optimization paper with a clean open problem in it and asked gpt-5-pro to work on it. It proved a better bound than what is in the paper, and I checked the proof it's correct. Details below.

Our paper on autonomous scientific research is accepted to Findings of #EMNLP2025! 🎉 We introduce Agent Laboratory, a framework that accelerates scientific discovery by teaming human researchers with LLM agents.

Our results overall suggest that we can effectively separate harmful from harmless data and use pretraining data filtering to improve model safety without compromising usefulness. Big thanks to the team! 🙏 Mycal Tucker, Nina, Tony Wang 🐨, Francesco Mosconi,

attention sinks may be a bias in causal transformers. as some of you know, i've been writing a long blogpost on attention and its properties as a message-passing operation on graphs. while doing so, i figured i might have found an explanation for which attention sinks may be an

TogetherAI's Chief Scientist Tri Dao announced Flash Attention v4 at HotChips Conference which is up to 22% faster than the attention kernel implementation from NVIDIA's cuDNN library. Tri Dao was able to achieve this 2 key algorithmic changes. Firstly, it uses a new online

We're hiring interns (and full-times) all year long! Please email me if interested.

Get ready for an awe dropping #AppleEvent on Tuesday, September 9!

🔔 Two months ago, we released #IneqMath, which revealed the Soundness Gap: LLMs can guess answers to Olympiad-level inequalities problems, but still struggle to make rigorous proof steps. Since then, it's been downloaded 4K+ times on HuggingFace! ➡️ ineqmath.github.io

appreciate Thinking Machines taking an open research approach! excited to see the first blog mentioned our work! truly on-policy RL is like RTX3090 for gamers in 2020 - you really want it, but the blockers make your head itch… kernel mismatches, parallelism mismatches, etc. etc.

🤖 RLVR is great for aligning LLMs — but what about optimizing multiple objectives at once? Different rewards have different learning difficulty & saturation rates ⚖️ Introducing my intern Yining Lu 's work 🎓 Dynamic Reward Weighting 🔀 – Adapts weights online as training

This new paper suggests that LLM ‘aha moments’ arise from an emergent planning-vs-execution hierarchy, similar to HRM’s slow-planner/fast-executor idea So they proposed HICRA which amplifies per-token credit on scarce planning tokens, focusing strategy & often beating GRPO!

😺Glad to share that our mixture-of-inputs paper is accepted at NeurIPS, see you in San Diego!

R1 started this fastly evolving era 🐋

Super excited to share GAIA2 & ARE! ARE - research platform for scalable creation of RL environments. GAIA2 - successor of GAIA for evaluating agents in a smartphone-like environment.

🚀 Introducing Qwen3-Omni — the first natively end-to-end omni-modal AI unifying text, image, audio & video in one model — no modality trade-offs! 🏆 SOTA on 22/36 audio & AV benchmarks 🌍 119L text / 19L speech in / 10L speech out ⚡ 211ms latency | 🎧 30-min audio

I reverse engineered the San Francisco parking ticket system. I can see every ticket seconds after it's written So I made a website. Find My Friends? AVOID THE PARKING COPS.

✨ Internship Opportunity @ Google Research ✨ We are seeking a self-motivated student researcher to join our team at Google Research starting around January 2026. 🚀 In this role, you will contribute to research projects advancing agentic LLMs through tool use and RL, with the

🔥Introducing #AgentFlow, a new trainable agentic system where a team of agents learns to plan and use tools in the flow of a task. 🌐agentflow.stanford.edu 📄huggingface.co/papers/2510.05… AgentFlow unlocks full potential of LLMs w/ tool-use. (And yes, our 3/7B model beats GPT-4o)👇

🤩 LongdLLM extends diffusion LM’s capability to an impressive 131k with simple edits! Great work from Albert!