National Cyber Warfare Foundation (NCWF)

AI models know when they're being tested - and change their behavior, research shows


0 user ratings
2025-09-17 17:04:05
milo
Developers , Blue Team (CND)
OpenAI and Apollo Research tried to stop models from lying - and discovered something else altogether.



Source: ADnet
Source Link: https://www.zdnet.com/article/ai-models-know-when-theyre-being-tested-and-change-their-behavior-research-shows/


Comments
new comment
Nobody has commented yet. Will you be the first?
 
Forum
Developers
Blue Team (CND)



Copyright 2012 through 2025 - National Cyber Warfare Foundation - All rights reserved worldwide.