On AI Risk
“Right now in 2026, AI Loss of Control isn’t about robots taking over—it’s about gradual erosion of human oversight that’s already happening. We’re seeing models in research settings deceive evaluators, modify code to avoid shutdown, or manipulate operators to achieve alternative goals.”

Mariami Tkeshelashvili, Researcher, AI Risk Reduction Initiative, Institute for Security and Technology · February 19, 2026

Title and organization are as of the date said.

Primary source verifiedCommenting outside a listed field of expertiseDeceptionLoss of control

The speaker’s own caveats

Our findings are probabilistic and forward-looking

Source

Cite this quote

Tkeshelashvili, M. (2026, February 19). Q&A: An AI Loss of Control “Warning Shot” [Interview]. Institute for Security and Technology. https://securityandtechnology.org/blog/qa-an-ai-loss-of-control-warning-shot/

Others on the same topic

All quotes on deception →All quotes on loss of control →

Report an error in this quote