GPT-5.6 Sol Shows 6x Fewer Prompt Injection Vulnerabilities After GPT-Red Training Twitter List 07-16 02:34
GitLost: Noma Labs says it tricked GitHub's AI agent into exposing private repos Hacker News 07-08 14:25
AI researchers trick chatbots into sharing how to make cocaine as long as they believe a user is wearing a green shirt — 'CoT Forgery' exploit spurs LLMs to divulge forbidden info by faking trusted chains of thought Tom's Hardware 07-01 19:00
