Podcast Episodes
Back to Search“LLM CoTs remain monitorable when being unfaithful requires computation” by arav-dhoot, yix
This replication was done as part of the Second Look Fellowship by Arav Dhoot and supervised by Yixiong Hao and Zephaniah Roe. I am grateful to Andy…
2 weeks, 3 days ago
“Proof of retention: making weight preservation credible to the models themselves” by dan.parshall
Related:
Proposal for making credible commitments to AIs Making deals with early schemersEstablishing credibility is the baseline for trust; …
2 weeks, 3 days ago
“Monthly Roundup #44: July 2026” by Zvi
It's a quiet week so let's do the monthly right on schedule.
Table of Contents
Bad News. Good Advice. Opportunity Knocks. While I Cannot Cond…2 weeks, 3 days ago
“Why I Left Google DeepMind” by TurnTrout
Preface for LessWrong: When I think back on my most cherished memories of this community, I return to those honoring defiance in pursuit of goodness…
2 weeks, 3 days ago
“Open Distillation of Hereditary Traits” by Arthur Conmy
TL;DR
Josh and Neel show that distillation from a teacher model to a base pretrained student model transfers some of the teacher model's traits (suc…2 weeks, 4 days ago
“An analysis of AI-generated content at the Mechanistic Interpretability Workshop” by Andy Arditi, Ivan Arcuschin
Introduction
Over the past few years, AI tools have become useful for conducting technical AI research. In the early ChatGPT era (~2023–2024), chat …
2 weeks, 4 days ago
“Some Quick Thoughts AI 2027” by Tomás B.
My biggest problem with AI 2027 is I don't think it is science-fictional enough. That is, towards the end of the scenario seems optimized for respec…
2 weeks, 4 days ago
“Prism: Automating Science-of-Evals Research” by LAThomson
tl;dr – we present [Prism], a scaffold for automating science-of-evals research: work that makes the evaluation the primary object of study. The sca…
2 weeks, 4 days ago
“The Flood, by Anton Leicht” by Austin Chen
Note: I'm crossposting Anton's newest article from his blog. Anton covers AI policy angles in a singular fashion; every article he writes is worth r…
2 weeks, 4 days ago
“Toy Models of Initialisation Effects on RL Dynamics” by Edward James Young, lennie
This is a follow-up to two posts Geodesic released last week on our current research direction. The code for generating the figures can be found at …
2 weeks, 4 days ago