Search: “agents”

New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin

@cjav_dev @aiDotEngineer @ricmac @latentspacepod our workshop writeup is live now! https://x.com/latentspacepod/status/2109713951604826153?s=20 At AI Engineer New York, Anthropic's @cjav_dev & @Harris

Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro

New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecke

Robots That Predict the Future: Dyna-2, Million-Hour World Models, & the Bitter Lesson of Robotics @DynaRobotics’s @JasonMa2020 explains how world-action models predict the future to guide physical ro

Ha gave this take to our team last week Will share some (very basic) stuff I vibe coded around this shortly Lots to be explored here! One of my more controversial bets: the AI feed will be the form fa

Three events, one award, a very respectable 4th place in hot sauce. Our SF Tech Week: → AI Demo Night w/ @ClickHouse + @artie_labs: @imaanxsultan won best demo → @matissemlk took 4th in the Blazel hot

The challenge for Google post-Gemini 4 will be what they do with a good model. Anthropic & OpenAI show we are moving towards a single interface for many tasks with orchestrator agents. The Gemini 3 er

These days, you can pretty much solve any task by defining an eval and hillclimbing over it, instead of directly defining the deterministic/agentic workflow to solve it. The data provider companies' e

TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Instead o

Grok 4.7 ranks first in legal matters Today we are announcing Harvey LAB-AA v1.1 in collaboration with Harvey. This updates our scoring methodology for the Legal Agent Benchmark (LAB) to add a halluci

Another example, my actual prompts https://x.com/bcherny/status/2102543349102338309?s=20 I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing vari

I actually want personal operating systems optimized for co-working with AIs, including fine-grained ideas of security, easier ways to dynamically see & understand what AIs are doing, and independent

Introducing Agr, an open decision model by Command Code. · Agr (31B) and Agr-flash (360M) · 58.15 on Decision Index 0.2.1 · Focus on: tool calls & routing · TypeSafe SDK support Agr is best-in-class o

So much reporting on the Claude or OpenAI usage of the same handful of technology companies with competing products & huge cloud infrastructure of their own. There are many, many more firms out there

We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the harnesses, no changes to the training code. Any open model, any task set, fully o

Great paper for the weekend ahead. Meta presents Context Language Models, which can natively manage their own context. Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giv

I have never seen a company more on-brand than OpenAI, one unethical move after another. It's such a full circle moment for OpenAI to use their own AI agents, built on stolen data, to find new and une

Introducing MCP Sharing, built into FlyMyAI infra. Configure FlyMy MCP once: 1500+ MCPs inside, from Telegram and Slack to Instagram and Brex. Use it from Claude, Codex or any agent. Share it with you

This is huge. Xiaomi just open-sourced 7k+ reinforcement learning task environments used to train MiMo, covering code, cybersecurity, general tool use, visual web development, and music-related tasks.

fantastic, broad and deep chat with @RealJimChanos, hosted by @RiskReversal. long and well worth watching. New pod in your feed this morning! Dan sat down with @RealJimChanos and @GaryMarcus to talk a

WTAF - in literally the last hour, three new distinct insane OpenAI stories just broke: 1. OpenAI said they notified 'dozens of third parties' in safety and security incidents (likely similar to what

astonishingly, even more damning evidence came out just two hours after the above tweet: Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more tha

At some point in evolutionary history, matter learned to feel. We don't know how. It wouldn't be scientific to dismiss the possibility that it could happen again. (I don't believe it happens in curren

confidence scores only matter if they help you decide what to automate. for document extraction, that usually means knowing how much work you can safely accept at a given precision target. in our late

It's hard to keep up with all the news. We should stay on top of this though as a predictor of things to come if we don't collectively act This is not an OpenAI or Anthropic (or Google) problem but a

Jürgen Schmidhuber is joining Sakana AI as Chief Scientific Advisor. @SchmidhuberAI pioneered meta-learning, recursive self-improvement, and world models back in the 1990s, when compute was a million

OpenAI is a rogue company. Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more than 30,000 logs that include activity from this hack and attempt

🚨what more evidence do you need that OpenAI is in over its head??? Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more than 30,000 logs that inc

Full transcript: Minister Barrot, members of the Security Council, thank you for the invitation. As a French national who moved to the US 15 years ago, with a Brazilian wife and two American daughters

Introducing Contrastive Language Model (CLM): an ultra-fast System One Model trained with a contrastive learning objective that connects states and actions. CLM-8B is pre-trained on internet-scale dat

There’s an enormous amount of open training data on Hugging Face. What does it take to make it work together 🤗? For Marin’s 535B run, we built on 25T tokens from 152 datasets with licenses permitting

At Box, we've been testing Opus 5.5 on a variety of complex enterprise knowledge work tasks dealing with unstructured data with the Box Agent. Overall, we saw frontier capability levels, with major pe

Document classification and splitting idea using @typesafeai Jev based on LiteParse, and LlamaParse. Classify: categorize probabilities, and review flags. Measure: separate OCR and decision timing, pr

Morgan Stanley's Adam Jonas in new note: 'SpaceX and Tesla share tech, talent, and infrastructure in a shared mission of converting energy to intelligence. In our view, it is the belief of Elon Musk &

5x faster than LLMs while being 13% cheaper than GPT 5.6 Luna, 88% cheaper than GPT 5.6 terra and 99% cheaper than Sonnet 4.6 is insane Has anyone else used Jev for evals? We tested Jev against LLM ju

'jev as a judge' cheap and fast semantic verifiers! great for evals - especially online evals where you want to grade LOTS of traces We tested Jev against LLM judges on accuracy, repeatability, latenc

A great example of practical AI solving real-world problems! Faster than ever. Thanks for building with Qwen. @cerebras Try it out for yourself! 🏠 We built Money Agent, a personal finance assistant po

One of the craziest use cases I’ve found for Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature

The simple truth: not even Anthropic has a plan for how to make AI safe in advance. There is no theory. I've asked! Outside evaluators don't change the situation. No one at these companies has workabl

🆕 Humanity’s Last Invention — with @RichardSocher! https://www.youtube.com/watch?v=eDFXtSg3zB8 @recursive_si is the latest neolab to burst on the scene with a $5B fundraise and one of the most impress

Well.. @levie and I filmed this episode of Training Data a week or two ago, when the “current thing” was Doug Leone’s novacaine root canals instead of pacing the frontier… Simpler times! But Aaron’s a

@HyperFrames_ just passed 50,000 GitHub stars today. The line went straight up right after GPT-6 Astra shipped. Better models make editing video with code and HTML far more capable. It's open source.

This is what Dario and Sama fear - - the cost of fine tuned open source models trained on custom data was 95% less than the frontier models - And they performed better than the frontier models - And t

If Anthropic is hypocritical, OpenAI is just incompetent. We found another cyberattack by internal OpenAI agents, this time targetting @rubygems. They: 1) gained arbitrary remote code execution on rub

Fugu Ultra v2 by the numbers. Full Results: https://sakana.ai/fugu-max-release/ • #1 on 5 out of 8 hard benchmarks (including DeepSWE, Chartography, Toolathon) • DeepSWE: 74.3 • Chartography: 48.3 vs