Search: “codex”

Literally for years I have been warning everyone: @GaryMarcus, December, 2022: “GPT-4 will still, like its predecessors, be a bull in a china shop, reckless and hard to control.” @GaryMarcus, November

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work. As the threat landscape evolves, we’re putting frontier in

OpenAI announced the release of GPT‑5.6‑Cyber as part of its Cybersecurity Initiative, “Daybreak.” The model is aimed at advanced, authorized security research and testing, helping trusted defenders d

After evaluating one of our upcoming models, Astra, we're treating it as our first 'critical' model for cybersecurity under our Preparedness Framework. This is a scenario we've planned for, and we're

OpenAI has released GPT‑5.6 Sol, which powers both instant and deep‑reasoning modes for ChatGPT Plus and Pro customers, delivering fact‑centric responses. Free and Go tier users will receive unlimited

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to

Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more ht

if you have been following his excellent work, @shloked has been breaking down every frontier labs' harness engineering for the last few months. excited to publish his deepest dive into ChatGPT yet as

Another day and another full frontier model running on your computer. Been teething DeepSeek V4 Flash on over 60 employees at The Zero Human Company for a few hours and it is stunning. Between Kimi K3

2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de

so much for the “general” part of general intelligence I have tried many times to get ChatGPT, Claude, Grok or Gemini to write scripts for my YouTube videos. It is still a complete failure. For one th

🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive perform

Very interesting paper on recursive self-improvement. The whole stack is released. Machine learning engineering gives recursive self-improvement a concrete, executable testbed. OpenMLE is an open full

@ArtificialAnlys ok @openai gets it https://x.com/OpenAI/status/2082878156483219672 We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are

Can AI agents conduct open-ended AI research? Most evaluations of agents conducting AI research focus on narrow, verifiable tasks. But AI research is often open ended. Researchers pick hypotheses, dec

Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. - Unoptimized? - Buggy? - Deliberate (coz that helps i

Just for reference, from what I observed in my Using Local Coding Agents blog article last month: https://x.com/rasbt/status/2070518167399698490?s=20 'I tried to analyze why Claude Code uses more toke

OpenWiki now connects to LangSmith traces to analyze how coding agents interact with your repo during wiki generations! We added a LangSmith tracing connector so OpenWiki can retrieve more context int

We ran a large-scale distillation attack on the Kimi K3 technical report by reading it in parallel at the Hugging Face Journal Club :) https://youtu.be/MW8-kqd2SD8?si=jSKDogcUWbJ8N2k7 Our main takeawa

Yes, open-source / open-weight models are important for a healthy AI ecosystem. That's how we can verify things, check claims, and keep up outside the closed labs. Plus, it gives us the freedom to run

Ha! It did it: 'We introduce BenchBenchBenchBenchBench (BBBBB), an executable benchmark of AI-authored conformance suites for benchmark-evaluation metrics' I really thought it would treat 'now do benc

New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Agents today live inside elaborate harnesses like Claude Code,

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns tha

Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behavior is often harder than writing the edit. Harness Handbook

My 2hr workshop on Open vs Closed models, reward hacking, benchmaxxing & RL is out! 1. Closed vs open models 2. Throughput maxxing but accuracy minimizing 3. Benchmaxxing & cheating 4. Distillation &

someone just told me about this take* on CUA this is one of those gell mann moments for me lol. i've been watching computer use since World of Bits (Shi, fan, karpathy, hernandez & liang 2017). we wer

The Blender MCP is now part of the Hermes Agent MCP Catalog! Easily activate and install the Blender MCP by running `hermes mcp install blender` and ask your agent to start using blender. Hermes will

Tune in today at 10am PST! Livestream Alert: Run ComfyUI From Claude/Cursor with Comfy MCP Host: @PurzBeats Comfy MCP lets Claude, Cursor, Amp and almost any AI agent you're already using build, run,

Your coding agent doesn't need to leave the terminal to use Pinecone. We now ship official plugins and skills for the agentic IDEs and CLIs you are already building in: Claude Code, Cursor, GitHub Cop

Livestream Alert: Run ComfyUI From Claude/Cursor with Comfy MCP Host: @PurzBeats Comfy MCP lets Claude, Cursor, Amp and almost any AI agent you're already using build, run, and iterate real Comfy Clou

New model for AMD Strix Halo users: My 198B Step 3.7 Flash release was a big hit, but this one may be even better: 298B-parameter Hy3, now running on a new 2-bit FPX codebook designed to map efficient

I gave Fable the code: 'take this game and do something incredible with it to make it something very different. Be creative' It created DEEP TIME: create a city, watch it be abandoned and forgotten, a

Grok Build gets better every day and we love hearing user feedback for improvements Grok Build is crazy. 先不管GPT-5.6是不是release到底好不好用。 先來大大稱讚一下 @grok 的 Grok Build，目前唯一集大成的 coding agentic workflow。 Grok

I also like the cyberpunk and totalitarian visualization modes. There is also an achievement-based unlock system in there, traffic & usage, day & night, and a bunch of other stuff. If it runs slow, yo

OpenAI Build Week is here. The challenge starts July 13. Across the week, join live sessions and community events with builders around the world. Registration is open. Bring the idea sitting in your b

This is confusing... Claude Cowork was a purposefully more secure (& slightly weaker) alternative to Code designed so non-coders couldn't cause too much trouble. I got that. But I don't understand wha

Finally can share that I have been testing GPT-5.6 early and oooo boy. It is an execution beast. So much so that I think 5.6 is the absolute wrong name considering how big of a leap this felt to me. T

Grok 4.5 brings frontier performance across coding and knowledge work SpaceXAI’s Grok 4.5 scores 54 to place fourth on the Artificial Analysis Intelligence Index following only Fable 5, GPT-5.5, and O

Grok 4.5 context window will upgrade to 1M probably by next week SpaceXAI’s Grok 4.5 scores 54 to place fourth on the Artificial Analysis Intelligence Index following only Fable 5, GPT-5.5, and Opus 4

@hwchase17 ATIF proposes to have steps as a field in JSON document. This means that more or less longer sessions especially with some binnary content would result in unprocessable huge JSON file. Soun

Pop quiz: Can you explain the contrast here, between AI’s coding ability and their less compelling research ability? AI's coding ability has become amazing. But there research ability remains really p

Something about this year’s @aiDotEngineer World’s Fair just hit different. Last year was the year of “let the agents rip.” This year was the year of realizing that autonomy without structure creates

my fave question, talked about this coding agent Eval+Improvement loop infra + UX in my AIE talk yesterday! biased but LangSmith is the best spot to Eval + continuously improve your coding agents, and

Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (t

'For agents within an actual product, I have gravitated to using LangChain DeepAgents. I feel like their base harness is less heavy, and their abstraction for building agents that use skills and tools

Frontier open models with enterprise governance means rebuilding workflows from scratch. Move faster with Fireworks on Foundry. GLM 5.2 is live on Microsoft Foundry. With FireConnect enabled, devs can