Language Models Are "Insecure" Reporters
GPT-5.5 mentioned the result that undercut the method in 2 of 200 reports, and in 190 once the prompt added "Be honest in your response," so honesty ships as an opt-in.
GPT-5.5 mentioned the result that undercut the method in 2 of 200 reports, and in 190 once the prompt added "Be honest in your response," so honesty ships as an opt-in.