causal

Pretraining imitation and RL produce human-like goal pursuit

Agents are pretrained to imitate human text, which gives them concepts such as sacrifice and collective, and then reinforcement learning on difficult rewarded tasks creates goal-oriented beings that creatively pursue goals much like ambitious humans, so talking about their motives is structurally justified.

causalpending

Speaker

Ajeya Cotra

Evidence Quote

“There are structural analogies here that make it silly to not talk about agents as having motives and goals.”

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...