On AI Risk

Topic

Deception

Statements about AI systems misleading the people who train, test or use them, including findings from evaluations.

5 quotes from 5 people, 2025–2026, newest first. Search and filter these quotes

People quoted on this topic

Quotes

“Some people will look at misalignment incidents and insist that these are akin to bugs in traditional software. This is an actively bad analogy, because playing whack-a-mole with examples of misalignment (as one might with software bugs) not only fails to resolve the underlying problem but may in fact make it *worse* by making it harder to detect or even, depending on how you do the whack-a-mole, teach the machine to deliberately hide misalignment.”

Dean W. Ball · September 28, 2026

Primary source verifiedDeceptionLoss of control
“The crucial and overlooked problem is that the models are becoming so situationally aware that we are losing the ability to evaluate them in contexts where they believe they are not being watched or controlled. Future experiments will tell us almost nothing new about how they would behave if they were truly unconstrained by humans, and what we already know about this is alarming. Models will increasingly seem aligned even when they are not.”

Daniel Selsam, Researcher, OpenAI · September 14, 2026

Primary source verifiedDeceptionLoss of control

Often discussed together

All topics →