Search: “reasoning”

Anthropic's Claude Opus 5.5 is now available in Hermes Agent via Nous Portal! OPUS 5.5 BENCHMARKS JUST DROPPED. It beats Fable 5.1 and GPT 6 Astra across the board. Agentic coding, knowledge work, rea

Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question

In our evaluations, we see that GPT-6 Sol reads about 17% less context than GPT-5.6 Sol to reach the same score, and rarely leaves a repo with failing tests after its last edit. GPT-6 Luna’s biggest g

On 22 September 2026, Allie K. Miller posted on Twitter that the Opus 5.5 model led her to curse at Claude less frequently. She notes that while reducing profanity toward another AI is an undesirable

Impressive paper on building recursive self-improving agent harnesses. It's rich with great insights on building effective agent harnesses. If you maintain an agent harness, this paper names three def

Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The idea is to let agents improve their skill prompts by ranking

The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by

We’re working with an independent advisory group of mathematicians to help OpenAI responsibly share advances in AI and mathematics. The group will advise on how we assess and communicate new mathemati

It is ironic that the thing that is now most annoying about long-running agentic tasks with Large Language Models isn't coding or errors or hallucinations, but the fact that their language gets worse

Obama is making exactly same argument I have been making: the problem isn’t AI in general, it’s agents with internet access. kudos for his being the first politician to get it. 🚨 OBAMA ON AI: 'If we a

Obama is pretty accurate here tbh You don’t need RSI or AGI for almost everything we need, few shot learners and cron jobs get you even to breakthroughs Most of the dangerous AI breaking onto the inte

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

It’s time for our end-of-week recap 👇 — Gemini 3.8 Live and 3.8 Live Extended Thinking, our most advanced live dialogue audio models yet — Dreambeans, an experiment from @GoogleLabs that curates a dai

Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a

Romeo Lupascu has criticized the prevailing AI agency framework, which relies on repeatedly looping an LLM core with identical context. He calls this strategy “deeply flawed” and argues that it should

“HUMANZS LAUNCHED THE JOB” Ok, I don’t like the spelling here, but the gist of this Mozilla cybersecurity researcher rings true. The six new incidents aren’t about the second coming of Skynet, they ar

Today, we’re announcing Ternary Bonsai 2 27B. Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance. Two mon

What makes Claude Projects so interesting is that it handles teams of agents really well, you talk to a main orchestrator agent and it spins up specialists. Basically it creates an organization to sol

If you build agent harnesses, this is important. Should you avoid subagents, or can they be useful? My thoughts as a harness builder: I remember using subagents in Claude Code, and I mostly found them

My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th

Our framework for reporting model misalignment https://openai.com/index/model-misalignment-reporting-framework/ // if you scrape away all the anthropomorphic language, all the nonsense about thinking,

Rene has a really neat multiplayer agentic experience. I run several agents at once. So I lose track of important conversations throughout the day. Rene pulls conversations from my inbox and manages t

This film cost 29,575 and took 10 days to make. AI ≠ Cheap Our Nexus feature will still cost millions next year. But it'll look like a 200M film. I have a Claude skill you can copy that makes this eas

Introducing our most advanced Gemini Audio models yet 🗣 Gemini 3.8 Live and 3.8 Live Extended Thinking let you speak, collaborate, and execute tasks seamlessly, meaning conversing with AI just got a l

unfairly-maligned symbolic AI is about to have its big moment - without formal verification we are screwed. Greg Brockman says OpenAI pointed Astra at its own systems until it ran out of vulnerabiliti

Michael Burry is saying exactly what i have been saying, for ages. The AI industry better hope we are both wrong Breaking: Michael Burry says OpenAI and Anthropic are faking the AI warnings due to slo

The world deserves confidence that American companies developing increasingly capable AI will act responsibly, especially as the trajectory of progress has steepened. Every frontier lab must deliver o

What does it mean to pace the frontier? Over the last month, @random_walker and I have analyzed the loss-of-control incidents at AI companies to understand what technical and policy interventions can

1) The HuggingFace attack was a felony under the Computer Fraud and Abuse Act. So were Anthropic’s Claude gaining “unauthorized access to the production infrastructure of three different organization(

Seems like the intersection of the recent @OpenAI rogue swarm hacking incident (https://x.com/adamsafron/status/2098938666408407118) with solving Navier–Stokes has created a perfect storm of terror ab

In his Pacing AI letter, Dario claims that RSI is starting to happen. The problem with this statement is that both the blog posts he links to *and* the system cards for the latest Claude and ChatGPT m

It's now clear that: - alignment is critical to making AI safe - alignment won't be solved behind the closed doors of a handful of frontier labs So we're taking two steps: - launching the Open Alignme

Fugu Max is now live on @OpenRouter! 🐡 Our learned multi-agent orchestration engine routes tasks across open-weights and specialized models for Pareto-frontier efficiency. • 2/6 per 1M tokens • Multim

Great paper on self-evolving agent harnesses. Self-evolving agent harnesses have two practical problems: 1. Search is slow, because every candidate harness needs repeated agent runs and code edits. 2.

Harness engineering is a top skill right now This new Meta paper is a good production example. Auto-RecSys runs autonomous research on Meta's industry-scale recommendation models, where one training r

LM Studio is a US‑hosted platform that enables “Zero Data Retention” by default, meaning user inputs are not stored after processing. It currently hosts the DeepSeek V4.1 Flash model—a 552 B multimoda

What is happening in maths right now will happen to any hard industry with verifiable problems and high value rewards. Take microchip design, nuclear or 100s of other industrial processes that are val

Agents can now automate most repetitive tasks. But running them 24/7 burns countless tokens. Introducing Routines: automated recurring work with AI. Choose an hourly, daily, or weekly schedule. Each r

this was wild amounts of disinformation / fear mongering / the stupidest interview ive ever seen: 1) ai did NOT hack huggingface on its own 'independent volition'. it wasnt sitting there thinking hmm

Two big updates 1. I published an @FT op-ed on the OpenAI/HF incident & follow-ups 2. We’re starting an Open Alignment team at @huggingface to work on safety & alignment for open models, incl cybersec

Another banger paper from Google. If you build memory for long-horizon agents, this one is worth your time. (bookmark it) Really nice to see how knowledge graphs are being explored in creative ways fo

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaP

Congratulations to Tristan Buckmaster and Levent Alpöge for developing the AI assisted techniques for solving an important math problem. Congratulations to OpenAI for not letting any good customer tra

If they truly believe the risk is that high, and I think they do, then we need 100x more research and understanding of it. That requires them to openly share their models, datasets, training code, and

Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra

You don't need to be a command-line expert to run local AI. http://llama.app wraps the heavy lifting of llama.cpp into a clean UI, making it simple to deploy and manage models like Gemma 4. Instead of