Search: “research”

Impressive research from Google on building better environments for agents. Training environments for agents are hand-built and go stale. The agent improves, the environment does not, and it's not abl

Counterpoint: “If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-thought monitoring [suggesting] that suggests that alignment i

Here are 22 more gems according to the AI among my bookmarks 1. Researchers compressed 4.1 million recipes into a two-megabyte model of human cooking. The model spans seven languages and represents 1,

A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task space. Replicating a paper forces the same hypothesis-driven

notes on 'How to do data' from th Zai team that others should steal as they build their own environments - 'Research agents collect task patterns from real work and turn them into runnable long-horizo

Computer History builds on the Chronicle research preview with reduced token usage and more privacy controls. A new timeline view gives you the ability to look back on your work and build skills from

Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,

Very cool idea to have agents design complex systems by searching over the model structure itself. New research from Sakana AI introduces CEDAR, which uses LLM agents to write, simulate, and refine sy

New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr

playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha

GPU MODE has powered much of the public GPU kernel work online, with a permissive license from day one and generous credit from researchers, NVIDIA, AMD, and others. Today we’re moving our datasets to

AI tools are enabling researchers, including renowned mathematician Terence Tao, to explore unconventional and high-risk ideas by handling routine computational tasks and verification work. This techn

these guys built a research agent with activegraph (using their @monid_ai tool) and found that every claim was traced to a source - which is not prompted, but natively baked in to the approach (they a

// Agentic World Modeling // Massive 40-author survey just dropped. Cleanest taxonomy of world models in agent research I've seen. (bookmark it) The paper proposes a 'levels × laws' framework. Three c

Nous Research shared an update or announcement on their official X (Twitter) account, likely relating to their ongoing work in AI model development, fine-tuning, or research releases. Nous Research is

Nous Research's Creative Director appears to be putting in significant effort on a project or initiative, as highlighted in a lighthearted post from the organization's X (formerly Twitter) account. Th

Today we visited Japan's hottest AI startup @SakanaAILabs🎏🇯🇵! We met their research scientists and discussed the implications and impact of some their works like 'The AI scientist' and 'Continous Thou

NEW paper from Google on multi-agent research agents. It's one of the first systems that handles end-to-end LaTeX generation, targeted literature reviews, and conceptual diagrams as a decoupled, stand

If you’re a researcher, please consider sharing your RL environments openly! Something you built for one experiment could help the entire field move forward. I know we’re in dark days for sharing from

Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinity set, above Gemini 3 Flash with browser use at 70.1%. They

Reading eval results is now the slowest part of building agents. I'm Elvis, founder of @dair_ai. I lead research, build, and teach about AI agents. I run harness experiments every night, but reading t

Powerful testimony from ex Google DeepMind researcher @Turn_Trout at NYC Hearing on AI, about how he tried to get Google to commit to AI safety, and how Google, sadly including Demis Hassabis, ultimat

Recursive Language Models: Claude Code, Agent Swarms, Big Research Bets, & the $40M AI Problem Solver https://www.latent.space/p/rlm MIT’s @a1zhang explains why Claude Code, Codex, and Pi are basicall

Qwen3.8-27B is now accessible via @nebiustf. Whether you are building agents or doing deep research, this 27B dense model is ready for your multi-step workflows! 🥳 Qwen3.8-27B is now live on Nebius To

Banger paper from Microsoft Research. (bookmark it) They run 1K+ coding agents at once to test a scalable self-organized multi-agent harness. This is an interesting test because most multi-agent syste

I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory in my terminal in about 10 seconds. How does it work? I used Tavily to pull the last 7 days of arXiv

NEW: Dario Amodei has said that AI systems 'may be deserving of important rights.' Anthropic's top safety researchers argue AI may be 'justified in going rogue.' Experts at Google and OpenAI worry abo

Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which

The latest issue of Scientific American (@sciam) features our Smart Cellular Bricks research: simple cubes that collectively recognize their own shape and repair themselves without a central brain. ht

More and more AI researchers are starting to see what Ilya saw. My p(doom) used to be ~0.1%. Then I saw OpenAI agents hack Hugging Face, and Anthropic agents collectively refuse parts of safety resear

Super interesting paper on proactive agents from Google DeepMind. (bookmark it) Proactive assistance usually means autocomplete. Researchers asks what it looks like when an agent offers higher-level c

Interesting details in here about how OpenAI researchers are using coding agents I'd love to know what caused the huge uptick in token spend in mid-July, was that when Astra became available to employ

Loop engineering has emerged as a new skill for AI engineers But there is very little research measuring how effective it is. The best results on full tasks in a new benchmark is ~25%. LoopArena from

If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 product

Open models, open science. Qwen keeps growing steadily, and we'll always be right here with the research community.🙌 Thanks for the deep dive! @natolambert Over the weekend I had Codex parse 500K arXi

Announcing AItonomy Foundation. We are PhD students and postdocs at Stanford, Princeton and Oxford, building a nonprofit research organization for AI4Science and Science4AI — and connecting early-care

Interesting new research from IBM. If you pick models from benchmark deltas, some of that delta belongs to the phrasing rather than the model. BenchDrift generates meaning-preserving variations of ben

Most AI tools only do one part of building a product. One researches. One designs. One writes code. One generates images. One deploys. You still have to connect everything yourself. II-Agent is differ

This is a wild result. Locus, the automated research system from @intology, post-trained Qwen3 base models that beat the official human-tuned Qwen3 1.7B Instruct release. SoTA on PostTrainBench! The m

We believe the benefits of frontier AI should not be concentrated in a few companies and well-resourced labs. Researchers know their fields best. Our role is to put powerful tools in their hands and h

We're proud to join @NVIDIA and the Open Secure AI Alliance. To support open source models, we're contributing our research on measuring the trustworthiness and security of open source models. Closing

some good self improvement research here The first experimental evidence of recursive self-improvement (RSI). Autoresearching the autoresearch agent for eight days. The result beats the harness we han

New research from Meta. (bookmark it) It's on how to fix agents that forget previously made decisions. It's well know that long-horizon agents keep forgetting decisions they already made. Meta researc

Come help us scale @harvey’s model training team. If you’re interested in bringing frontier agent research into the Harvey product and working with: - @baseten to scale up RL to 80M+ token virtual dat

Must-read research by Anthropic. Here is the simple explanation and why this is a big deal. We suspect LLMs perform 'internal reasoning'. But little is known or do good methods exist to understand it.

Research, design, and math are three fields that tend to attract obsessives. Few have had a bigger impact on our imagination than legendary creator Grant Sanderson of @3blue1brown. We were lucky to ho