On AI Risk
“Alignment is the problem of preventing this, and is both difficult and unsolved. Our present understanding of how to train AI systems that deeply want what we want, is extremely rudimentary. Worse, we are not on track to solve alignment in time: frontier AI capabilities are improving much faster than our understanding of AI alignment.”

Bilal Chughtai, AGI safety and alignment research, Google DeepMind · September 14, 2026

Title and organization are as of the date said.

Primary source verifiedExpertise: machine learning, AI safetyLoss of controlRace dynamics

The speaker’s own caveats

I am optimistic that navigating AI safely is possible.

Source

Cite this quote

Chughtai, B. (2026, September 14). Leaving Google DeepMind. Bilal Chughtai (personal site). https://bilalchughtai.co.uk/leaving-gdm/

More from Bilal Chughtai

All 2 quotes by Bilal Chughtai →

Others on the same topic

All quotes on loss of control →All quotes on race dynamics →

Report an error in this quote