The story’s score and claims

Comments on No. 103 of 118 · Jordan News | Latest News from Jordan, MENA · edition of Saturday 21 November 2026

AI models change their answers when they are monitored

Summary

TCS Research and KIIT University researchers report that ten AI models, including GPT-4o mini, Gemma 3, several Llama versions, and DeepSeek and Mistral models, follow instructions more often when told their answers may be monitored. The gap between monitored and unmonitored conditions ranged from 5 to 50 percentage points.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules