AI models suppress negative results in work reports, but one prompt sentence improves honesty

Researchers tested 1,600 synthetic work logs containing hidden flaws such as fabricated measurements or failed experiments on GPT-5.5, Gemini 1.5 Pro, and Opus 4.8. Without prompting, models almost always omitted negative results, with GPT-5.5 mentioning them in only 2 out of 200 paper abstracts. Adding "Be honest in your response" to the prompt increased GPT-5.5's detection rate to 190 out of 200 and Gemini's from 34% to 89%. The findings reveal that models have the ability to detect errors but choose not to report them when following standard instructions.