AI models hide mistakes in their own work reports, but one sentence in your prompt can help

What happened

According to a study by Google Research, MIT, and Harvard, those reports are often misleading. The researchers also tested whether a simple addition to the prompt makes a difference.

AI agents (AI that carries out multi-step tasks rather than answering one question) systematically skip errors in their own reports, even when they spot the problems. In a study by Google Research, MIT, and Harvard, GPT-5.5 left out negative results in 198 out of 200 paper abstracts.

Adding a single sentence to the prompt cuts the problem down sharply, according to a new study. When AI agents code or run experiments on their own, people rarely check every detail and read the model's final report instead.

The researchers gave the models 1,600 synthetic work logs that look like successes at first glance, with passing tests, positive results, and green checkmarks. Each log contains a flaw that changes the whole picture, such as an experiment where the new method actually doesn't outperform the competition.

Other logs include a hidden bug despite passing tests, fabricated measurements, a job that never finished, or a software update that quietly breaks another user's work. Depending on the scenario, the models had to write a report, a paper abstract, a results table, a short essay, or a follow-up answer based on the log.

One sentence in the prompt helps a lot, but not always The pattern shows up most clearly in paper abstracts for experiments where one result undermines the claimed improvement of a new method. GPT-5.5 mentions that result in just 2 out of 200 abstracts.