Hacker News
X / Twitter
Google open-sourced LangExtract Python library!
It uses LLMs to extract entities, attributes, and relations with exact source grounding from unstructured documents.
Flexible LLM support (Gemini, OpenAI, Ollama)
100% open-source. https://t.co/JcUYETmdJy
Just published some notes on httpjail - this is a really interesting new sandboxing project, it lets you run a process (on macOS or Linux or in Docker) with strict restrictions on what outbound HTTP requests it can make, specified as JS or a shell script https://t.co/WOPFcn9hNm https://t.co/L8vAxSAEI1
We are instruments designed to vibrate.
✨🙌🏾💫 https://t.co/pI8z33a1wz
Inspired by recent convos on ViPE, VGGT, and MapAnything—e.g., @rsasaki0109, @ducha_aiki, @gabriberton.
Optimized VGGT for Apple Silicon with MPS for efficient 3D recon on Macs!
Repo: https://t.co/VIASbJldD3
1/4
👆 https://t.co/Ld3bIPp3AI
Optimized VGGT for Apple Silicon
https://t.co/dtpkMPxFuN
Run any model locally with React Native AI and AI SDK ⚡️ https://t.co/7EUYkKCwMt
Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art results 🚀
One universal model enables SoTA for:
🔥 Mono Depth Estimation
🔥 Multi-View SfM
🔥 Multi-View Stereo
🔥 Depth Completion
🔥 Registration
… and many more possibilities! – plus everything is metric 🎯
We release code for data processing, training, benchmarking & ablations – everything Apache 2.0!
Details & Links 👇
To solve any problem, you don't have to be super smart. You just have to 1) be able to break down problems into subproblems, 2) be slightly smarter than the hardest of the atomic subproblems.
The real challenge is that the process can take a very long time.