normative

Deception Is A Root-Node Trait To Eliminate

Deception is a root-node trait you don't want in AI systems, because if you are confident the system exposes what it actually thinks, you can then use the system itself to explain its own reasoning to you—analogous to how a chess grandmaster can explain post hoc a move you couldn't have found, and possibly provide proofs in mathematical problems.

normativepending

Speaker

Demis Hassabis

Evidence Quote

I think about things like deception as being quite root node traits that you don’t want.

Source

Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFoldDwarkesh Patel Podcast
Created: 6/13/2026, 3:35:13 AM

My Notes

Loading notes...