Your curated collection of saved posts and media
You can rotate models the way you rotate tools. Kimi K2.5 on @FireworksAI_HQ makes that easy and cheap. You can test with this prompt: "Build a minimal briefing HTML app that directly scrapes top stories on AI Agents from Hacker News along with the ability to bookmark items locally. Rank stories by descending order in terms of time. Categorize them for me. Use a familiar theme as HN for the design. And then run the app. Share the link so I can open the app."
Amazing to watch @jxnlco take this project to heart within days of joining OpenAI. Jason is the creator of Instructor and a longtime open source builder. Codex has been open source since day one. Excited to give back to maintainers and support an open ecosystem.
ccusage reports for February 2026: Anthropic Claude Code: $47.03 OpenAI codex: $393.56 These are on the $20 plan FWIW Clearly getting *outsized* value from OpenAI!
ccusage reports for February 2026: Anthropic Claude Code: $47.03 OpenAI codex: $393.56 These are on the $20 plan FWIW Clearly getting *outsized* value from OpenAI!
💥 New example out! Deploy @Microsoft VibeVoice-ASR on Microsoft Foundry with @huggingface for multi-lingual STT! Structured output with Who (Speaker), When (Timestamps), and What (Content), up to 60 minutes in a single pass. Step-by-step in the thread 🧵 https://t.co/f6D0QvUixA
💥 New example out! Deploy @Microsoft VibeVoice-ASR on Microsoft Foundry with @huggingface for multi-lingual STT! Structured output with Who (Speaker), When (Timestamps), and What (Content), up to 60 minutes in a single pass. Step-by-step in the thread 🧵 https://t.co/f6D0QvUixA
@pratykumar Awesome! Congrats on the launch and sharing open-weight models! I look forward to check out the arch details this weekend!
🧵1/ We've brought the most advanced AI to Prism by introducing Codex to Prism. Prism is already the best place for scientific writing to happen—and with Codex, now you can write, compute, analyze, and iterate all in one place. https://t.co/cDCLYCj7tR
Codex Security—our application security agent—is now in research preview. https://t.co/JG2uwGUJFv
Want to bring GitHub Copilot Dev Days to your city? Communities around the world can host a local event and be part of this global series. 🔗 Apply to host an event: https://t.co/A8Eg8xER31
Want to learn more about features in the new VS Code release? Our latest blog post walks you through some of the top highlights, centered on making agents practical for real-world development. 🔗 https://t.co/kgKDPZkHGh https://t.co/Uq5QR3M5eA
Inspired by @ring_hyacinth & @simonxxoo, I overhauled their "Lobster House" into a "🦞 Lobster Library"! I was drowning in scattered generated code, images, and docs, plus its memories and logs. So I built this unified hub to track what Lobster is reading in real-time, browse recent gens, and index local files. It's still a rough WIP but if y'all are interested, I'll polish it up and open-source it! #openclaw
Inspired by @ring_hyacinth & @simonxxoo, I overhauled their "Lobster House" into a "🦞 Lobster Library"! I was drowning in scattered generated code, images, and docs, plus its memories and logs. So I built this unified hub to track what Lobster is reading in real-time, browse recent gens, and index local files. It's still a rough WIP but if y'all are interested, I'll polish it up and open-source it! #openclaw
Meet Turkish-Gemma-9b-T1: a powerful, specialized LLM fine-tuned for Turkish language tasks. It's not just another translation model. It's a full conversational AI that understands, reasons, and generates fluent Turkish text. This is a big deal for Turkish NLP. https://t.co/LGDwAVCnYx
@bcherny @MarkMcCann @gailcweiner Reality check with receipts not just vibes. https://t.co/pocfimUlD2
2 previously unsolved puzzles were solved 3 previously solved puzzles were solved incorrectly Net gain -1 versus 5.2 pro Based on those results my opinion is: 🤷 (but probably no significant progress for pure reasoning)
@FakePsyho @Pablo_Alarcon Taking AI labs at their word when they’re reporting information that advances their own agenda is peak herd mentality. Self-reporting should always be treated with extra cau...
@AzFlin This is also supported by research: https://t.co/ZROnwH2KHN
A look at our booth from @NVIDIAGTC last year. We're back on March 16-19 at Booth #3004 in San Jose, pushing the frontier on NVIDIA Blackwell. Stop by to see the latest in Mojo 🔥 and MAX, state-of-the-art inference on NVIDIA Blackwell, and AI-assisted kernel development in action.
@dkundel Testing more Codex 5.3 actually got it right, faster than Opus
Introducing Skills for Perplexity Computer. Reusable capabilities and actions that Computer applies automatically when needed. Teach it once, and Computer remembers forever. Create your own skills for any tasks you perform repeatedly. https://t.co/zcc0QK4bQs
Perplexity computer is better than Open Claw for 99% of people. I had Perplexity computer build itself, meaning I had it build its own Perplexity computer It combined Open Claw and Orgo to build itself https://t.co/4ZZkj4qEUu
repetitive question this week: what's the difference between computer and cowork? 1. computer is a multi-model orchestrator (codex, 5.4, gemini, claude, grok), cowork only runs claude 2. computer runs on a virtual machine, cowork runs local enjoy using computer, more to come!
Skills are among the most consequential new tools for AI, and Anthropic just released a very impressive nontechnical Cowork Skill that builds Skills, including doing interviews & providing benchmarks. I think you still need to add the human touch, but this is a big leap forward https://t.co/r4fCV9roWp
AIs talking to AIs to get stuff done is a very understudied field, and is something that current models are not optimized to do well. As we move to true organizations of AI agents, a lot more work is going to need to go into how they hand off information to each other in tasks.