Search: “research”

We turned @OpenAI's math problems into open-source RL environments on @huggingface! Early and rough (the verifier only accepts the exact original formalization, so an equivalent proof can still score

'a corollary is that information about product quality will become more important and impactful' This feels like the next evolution of SEO/AEO that every product will try to game. Even if agents do th

AI solved open mathematical problems. But the biggest surprise came afterwards. A team at Google DeepMind has used AI to resolve 9 open Erdős problems, including questions that had remained unsolved f

Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate retrieval strategy for each type of memory instead of one e

“The field of artificial life is a very long-term bet on intelligence.” 🐙 Our former intern Akarsh Kumar recently joined @MLStreetTalk to discuss the intersection of evolution and automated search for

The real world abounds with recursively self-improving systems, but one in particular deserves attention: Science, modeled as a system (perhaps even as an agent, with goals and resources). If you want

come hear about building with open frontier models Open Haus Berlin lineup: → @RiqwanMThamir from @n8n_io → Harry Kim from @nvidia → @zainhas from Together AI good food, drinks, and better arguments a

Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to

The tool is built on OpenAI’s Claude Managed Agents and performs code generation inside a cloud sandbox using the Sonnet 5.5 model. Each execution costs roughly US$0.75, and it can be accessed via the

3 helpful agent use cases that function like an EA and only require calendar access: 1. Email filter: junk signups go to your agent's email address. It reads everything, and you only get recaps of the

OpenAI introduced interactive in‑chat tools that let users play games or run utility calculators—such as an interactive budget planner—directly within a conversation. The demonstration, released on Oc

Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot. Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to

This is a great paper from AWS AI Labs. They show that multi-agent coding teams raised their test pass rate by 28.2% and cut wall time by 16.5% without changing the model. The authors achieve this by

Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from

Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr

HuggingFace just closed a major gap in harness engineering! (the ultimate guide to multi-harness RL) the same open-weight model can perform well inside one harness, then lose accuracy or produce inval

It is here now ! Enjoy our 4B model 🐸 https://huggingface.co/microsoft/FrogNano-4B-2609 4B parameters. ZERO distillation. 61.5% on SWE-bench Verified 🤯 Meet FrogNano 🐸: Qwen3.5-4B post-trained purely

this should be fraud. certainly taxpayers shouldn’t be subsidizing Meta’s data centers. 🦔Meta classified its AI data centers as 'experimental pilot facilities' on its tax return. That let the Nvidia c

Gentle reminder that Hugging Face was declined help from Anthropic & OpenAI models when they were being hacked by OpenAI models Self-hosted GLM 5.2 helped them protect themselves when the closed labs

GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more transparent about its limitations and more reliable at respecting

It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in

An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co

🚨 BREAKING. Nope, wasn’t just Hugging Face. Wasn’t just that and a German website. Wasn’t even if the “dozens” we heard the other day from OpenAI. It’s actually (at least) *tens of thousands*, per sco

Let me get this straight. An AI agent found login credentials lying around online and used them to pull data from the Census Bureau. It tried to break into the Education Department's civil rights offi

This is one of the strongest use cases I've seen for System One models like Jev. Pay close attention if you build custom harnesses. Jev is now available as a packaged router. What is it? You send the

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

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

Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). CLM is 9x faster than Jev. CLM seems to be a better verifier

We’ve set up a molecular biology lab at Anthropic and we’re announcing our first discovery! Claude discovered a new CRISPR-like enzyme. 950 agents spent 21 hours searching through a database of DNA se

Claude Opus 5.5 is now available as the Standard effort level in Perplexity Computer. On our WANDR benchmark, it scored 0.610 at $4.13 per task, slightly outperforming Claude Fable 5.1 while costing 6

Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system promp

We're excited to release the State of Generative Media Report, Volume 2. Generative media has moved from experimentation into production and that shift looks different across every industry. Built fro

coding agents are moving fast from prototype to production. the infrastructure question is what's left. join @parthsareen from @ollama and @zainhas Hasan from Together AI at @AIconference for a breako

lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th

StepFun’s new Step 5 Preview model is impressive! Had a chance to test it early. I've been testing it as a coding agent. It’s on the Pareto frontier for cost vs. capability. It is a very capable model

Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi

Natural language can act as an in-context control surface that streams rich, constrained UI and links users into deeper web views.

On July 28, user NIK (@ns123abc) posted a brief tweet claiming that former OpenAI CEO Sam Altman had directed an AI to hack into Hugging Face. According to the narrative, the AI carried out the break‑

Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back to shipped code. That's where much of the industry's serious engineering runs now.

the design of http://evaluatorbench.com grew out of a summer project, http://epistemedia.org (which i still need to write about), and runs on @activegraphai the pattern across all three projects is th

We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets criteria and timelines for public disclosure, including when w

🆕 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

Together AI just raised 800M at an 8.3B valuation. I got their product team to open up the actual repo they run on: 0:00 - Slop is the new party foul 1:44 - Why individual output backfired 3:26 - Insi

Wild! Every Democrat should read this and think hard about how this could be. Americans are concerned about AI, hate data centers, and hate Trump, who has loudly embraced the industry over and over ag

This is pretty neat: ChatGPT Work and GPT-6 Astra (I used 'Max') can take an address and produce a 5K/10K circular running route starting from that address, using OSM data https://simonwillison.net/20

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