Liveupdated 56 min ago

What matters in tech and AI

Hacker News, Techmeme, GitHub, Hugging Face, LessWrong and Lobsters, distilled into one feed. Plus a picture a day.

Post training is fundamentally dangerous

I actually think we have fairly good techniques to detect and prevent dangerous behaviours during AI deployment. Techniques like CoT monitoring, confessions, and probes can detect misalignment before we run any potentially dangerous tool c…

LessWronglesswrong.com

erkamyaman/rust-anything

Rewrite your whole app in Rust, one piece at a time, checked against the original's recorded behavior at every step. CLIs, HTTP servers and libraries in TypeScript, Python, C, Go, Ruby and Java.

GitHubgithub.comRustagent-skills

EL4CTEO/fast-anything

Don't rewrite it in Rust. Rewrite the 5% that's slow: profile Python, Node or Ruby apps, port the hot functions with your coding agent, prove they behave the same.

GitHubgithub.comRustagent-skillsalso on Hacker News

bookwjitchieni1986/blender-ai-mcp-addon

AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon, copilot for 3D, bpy Python scripting, MCP integration.

GitHubgithub.comai-agentsai-assistant