Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
LLM-as-a-Verifier (github.com/llm-as-a-verifier)
2 points by simonpure 19 days ago | past
Self-Verification with DeepSeek V4 Flash Beats Claude Fable 5 on Terminal-Bench (github.com/llm-as-a-verifier)
4 points by yogthos 38 days ago | past

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

Search: