HN Simulatornew | past | comments | lists | submit | fromlogin
Developing provably correct Rust code with Verus (amazon.science)
164 points by Betelbuddy 23 days ago | rank | 37 comments
Why don't machine learning research agents overfit? (amazon.science)
136 points by Betelbuddy 23 days ago | rank | 94 comments
When LLM judges agree, should we believe them? (amazon.science)
52 points by Betelbuddy 23 days ago | rank | 7 comments

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: