Skip to content
AI IntelligenceOct 17, 2026AI Intelligence
Article

Study finds GPT-5.5 omitted negative results in 198 of 200 abstracts, one prompt sentence can help: A study by Google Research...

MIT and Harvard found AI agents systematically skipped errors in their own reports, even when they spotted them. GPT-5.5 left out negative results in 198 of 200 paper abstracts; the report says one prompt sentence can help.

Frontier EditorialSource: The Decoder
01

Source Brief

Study finds GPT-5.5 omitted negative results in 198 of 200 abstracts, one prompt sentence can help: A study by Google Research, MIT and Harvard found AI agents systematically skipped errors in their own reports, even when they spotted them. GPT-5.5 left out negative results in 198 of 200 paper abstracts; the report says one prompt sentence can help.