belluxx
Re:Why Is This Fingerprinting Script Creating Bioweapons?
on Wednesday October 28, 2026 @06:19PM (#50281723)
Do you have some resources to link on the easy ways you mentioned?
Re:DeepSeek-v4.1-Flash-1017
on Saturday October 17, 2026 @09:16AM (#50130910)
Pi is very good with open weight models (proprietary ones too)
Re:Watch AI materials-science and bioscience abilities closely
on Monday September 14, 2026 @09:36AM (#49696666)
Lately "one-shotting" means "without human steering / feedback"
I think its a consequence of the improvements in harnesses and LLMs of the last year. Before they had a hard time self-reviewing the results and proceeding to a second iteration, now they are quite good at it although not perfect.
Show HN: Nanointerpret – LLM Interpretability Playground
https://nanointerpret.pages.dev/
I find LLM interpretability extremely interesting and wanted to create a minimal repo for: - SAE training - Automatic feature interpretation - Visualizing features and running interventions through a GUIYou can try it here: https://nanointerpret.pages.dev/ Or check the repo: https://github.com/Belluxx/nanointerpret
Show HN: TransFire – Chat with your local LLMs without port-forwarding
Show HN: Local LLM AIME benchmarking tool
https://github.com/Belluxx/LocalAIME
I made this simple tool to compare local LLMs. Any provider that supports OpenAI-like APIs can be used (LMStudio, Llama.cpp, Ollama) but you can also use Openrouter/OpenAI if you change the base URL accordingly.In my opinion it is not particularly useful for comparing different models from different companies since some models are optimized heavily on math or even trained on AIME...