Your curated collection of saved posts and media
void-model has been awesomely trending on @huggingface this week! Please use it and let us know how we can make it better 🤗 https://t.co/4BwZKr975B https://t.co/r8XtGBglds
Gemma4 is a national treasure you’re all still sleeping on. GoogleDeepMind threw OSS AI a lifeline with the Gemma 4 class models. A week in and I can confidently attest, truly the best open model for its size by a long landslide. Connect your agents, thank me later.
VS Code March Release included several improvements to the editor experience. Check out our latest video for demos of Autopilot (Preview), Integrated Browser Debugging, Chat Customization (Preview), and Configurable Thinking Effort in the Model Picker ▶️ https://t.co/IT2xeM3xNX https://t.co/xw9wQiBju8
My drone story at the Pont du Gard - filmed with Seedance (via @Fal till I ran out of money hah) and Veo and Nano Banana. Surprising the things that were hard! https://t.co/wWgtsiqPGi
@HarryStebbings @jasonlk @asenkut @vivfaga @anuhariharan @jmj I love investing in dev tools because legacy products really suck & developers are vocal but loyal when a new solution is actually good Supabase, Metronome, WorkOS all companies I backed at seed because they solved a known problem with better solution
Our latest Live model is # 1 on Tau Voice Bench! Excited to see this new frontier of voice models cross the chasm of usability in production. https://t.co/wKphNSV6SL
This is HUGE. Ollama now supports Hermes AI Agents. A fully local self-improving AI Agent that runs for you 24/7 for free. https://t.co/GfsyY3kyDL
As promised, here's a recording of my 30-min keynote and the subsequent Q&A for the inaugural late interaction retrieval (LIR) workshop, cc @bclavie @antoine_chaffin. The talk is admittedly advanced, as it's directed at an expert IR community. But hopefully still broadly useful! https://t.co/jPI6306jMx
Lots of people interested in the late Interaction workshop, listening to @lateinteraction's keynote! https://t.co/fpN8qvFOLI
Gary Marcus 又放大招了！ 他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then 分支 + 确定性符号逻辑 Anthropic 在关键时刻还是靠经典符号 AI来保底，才让 Agent 真正可靠。 这波操作，等于直接验证了 Marcus 过去 20 多年一直喊的 Neurosymbolic AI（神经符号混合）路线！ Scaling 不再是唯一答案，混合路线才是未来 完整长文值得细读👇
Claude Code is not AGI, but it is the single biggest advance in AI since the LLM. But the thing is, Claude Code is NOT a pure LLM. And it’s not pure deep learning. Not even close. And that changes everything. The source code leak proves it. Tucked away at its center is a 3,1
🚀 Artifact Preview v3.0 just shipped for Hermes Agent! Just like Claude. Your agent writes HTML/CSS/JS → the browser opens automatically 🚀 → you see a polished, live, interactive preview. No manual steps. Zero friction. ⚡ https://t.co/b5SywJKty2 cc @NousResearch
