Savlar4 sources healthy · latest episode 20 Oct 2026
opinion claim

The speaker thinks neural networks do not appear to use a prior in which an AI only attempts tasks when it believes it is in training.

Ajeya Cotra · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sept 2026

In their words

The transcript segments this claim was taken from

“It doesn't seem like this is the prior that neural networks use,”
Play from 1:00:24Report a misattribution
80%how strongly it was put, not whether it is true
70%importance to the conversation
94%confidence the claim was read correctly