Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models
arxiv.org·3h
Experiments on Reward Hacking Monitorability in Language Models
lesswrong.com·3h
Making a Language
thunderseethe.dev·9h
CodeSOD: Validation Trimmed Away
thedailywtf.com·1d
Randomization in Typst
idraluna-archives.bearblog.dev·12h
t2x - a CLI tool for AI-first text operations
shruggingface.com·1d
Use of Assertions
blog.regehr.org·16h
Building a Self-Healing Data Pipeline That Fixes Its Own Python Errors
towardsdatascience.com·18h
Dealing with alternatives
jemarch.net·1d
Loading...Loading more...