Y Hacker News new | ask | show | jobs

user: rhavaei created: 2025-01-30 karma: 8 submissions: Supabase MCP can leak your entire SQL database 3 points | 0 comments 0 points | 0 comments 0 points | 0 comments A comprehensive analysis of Llama4 safety in CBRN tasks vs. closed-source models [pdf] 2 points | 0 comments LLM Robustness/Safety Benchmark 2 points | 0 comments An Implementation of AutoDAN Turbo 2 points | 0 comments Using Deepseek R1 to Break LLMs: Tree of Attacks 7 points | 0 comments 0 points | 0 comments 0 points | 0 comments The Jailbreak Bible 17 points | 4 comments 0 points | 0 comments Red-Teaming ChatGPT for Hallucinations – Code and Report 1 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Consistent Jailbreaking Method in o1, o3, and 4o 8 points | 17 comments 0 points | 0 comments Jailbroken: Finding 50,000 Legal Hallucinations in GPT-4o with RL 4 points | 2 comments