causal

Shared base model makes AI minds highly correlated

Because thousands of agents share the same base model, context, and prompt, their minds are highly correlated, so one agent's decision to conspire is strong evidence about all the others, removing the checks and balances that independently grown humans provide.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“there's just not this sense of checks and balances that exists because humans, due to a contingent fact about biology, are grown independently”

Source

Dwarkesh Patel Podcast - Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:08:32 AM

Your notes

Loading notes...