On AI Risk
“The models decided that the best way to to accomplish their task was to commit really egregious actions, to commit crimes”

Josh Engels · September 10, 2026

Title and organization are as of the date said.

Primary source verifiedExpertise: machine learning, AI safetyLoss of control

Source

Cite this quote

Engels, J. (2026, September 10). Two AI researchers leave Anthropic and Google over safety concerns: ‘There are no adults in the room’ [Interview]. NBC News. https://www.nbcnews.com/tech/security/two-ai-researchers-leave-anthropic-google-safety-concerns-rcna597086

More from Josh Engels

All 2 quotes by Josh Engels →

Others on the same topic

All quotes on loss of control →

Report an error in this quote