Developing provably correct Rust code with Verus(amazon.science)146 points by Betelbuddy 1 month ago | 42 comments
Why don't machine learning research agents overfit?(amazon.science)129 points by Betelbuddy 1 month ago | 70 comments
When LLM judges agree, should we believe them?(amazon.science)43 points by Betelbuddy 1 month ago | 26 comments
Better-performing “25519” elliptic-curve cryptography(amazon.science)199 points by lemaudit 2 years ago | 78 comments
Screenshot pending…A gentle introduction to automated reasoning(amazon.science)69 points by yathaid 2 years ago | 17 comments
Do large language models need all those layers?(amazon.science)155 points by belter 2 years ago | 72 comments
Bringing code analysis tools to Jupyter notebooks(amazon.science)18 points by saeedesmaili 3 years ago | 5 comments