“The AI Doc” is coming out March 26
On Thursday, March 26th, a major new AI documentary is coming out: The AI Doc:…
Category: Opinion
Helical Representations of Turn Structure in an LLM
This is adapted from my application for Neel Nanda's MATS 10.0 stream. It wasn't accepted,…
Teaching Models to Dream of Better Monitors through Monitor Sensitive Training
TL;DRWe introduce Monitor Sensitive Training (MST), a new post-training technique where we augment training data…
AI’s latest casualty – Peer Review & How to prevent more damage
TLDR: LLMs allow reviewers to outsource judgment without accountability; peer review breaks when judgment is…
Separating Prediction from Goal-Seeking
tl;dr: Mixing goal-directedness into cognitive processes that are working to truth-seek about possible futures tends…
Null Results From An Orexin RCT
Over the last few months we[1] have been doing a sleep experiment inspired by our suspicion…
Formal Verification: The Ultimate Fitness Function
This article is crossposted from Structure and Guarantees, my series on full-stack design of intelligent…
An interactive version of the extropians mailing list
Claude & I vibecoded an interface for the extropians mailing list. It’s live! Have a…
Metagaming matters for training, evaluation, and oversight
Following up on our previous work on verbalized eval awareness:we are sharing a post investigating…
Metagaming matters for training, evaluation, and oversight
Following up on our previous work on verbalized eval awareness:we are sharing a post investigating…