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
…The cocaine trick, which the authors call CoT Forgery, took jailbreak success from near zero to roughly 60% across every model tested and won the 2025 OpenAI GPT-OSS-20B red-teaming…