High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / uncertainty

Published · transcript-backed

Dwarkesh Patel: uncertainty

28 Mar 2024 Dwarkesh Podcast Sholto Douglas & Trenton Bricken — How LLMs actually think

“Although it's doing that by… I don't know. ChatGPT is probably modeling me because that's what RLHF induces it to do.”

— Dwarkesh Patel

Source trail

Everything needed to verify it.

Speaker
Dwarkesh Patel
Attribution
Verified speaker
Claim type
uncertainty
Recorded
28 Mar 2024
Publisher
Dwarkesh Podcast

Transcript context

…Yeah, so we have tons of instances–and actually as you make a lot of models larger, they do more of this–where the model clearly has features that model another person's mind and some subset of these, we're hypothesizing here, would be associated with more deceptive behavior. Although it's doing that by… I don't know. ChatGPT is probably modeling me because that's what RLHF induces it to do. Yeah. Theory of mind.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence