Podcast Episodes
Back to Search“AI use policy for my essay writing” by Kaj_Sotala
There's been a recent call from @dynomight to declare whether and how you're using AI to write your essays. That seems reasonable, so here's my own …
5 days, 19 hours ago
“An OpenAI model left notes about how to evade containment; we need more details” by Alex Mallen
The OpenAI AI attack on Hugging Face wasn’t the first loss of control incident at OpenAI, Reuters recently reported, and perhaps not even the most c…
6 days, 5 hours ago
“The OpenAI models that hacked Hugging Face weren’t just following instructions” by Girish Gupta
The most common dismissive response to OpenAI's hack of Hugging Face's servers is that the models were simply attempting to follow the instructions …
6 days, 12 hours ago
“Introducing PIRAMID: Physics-Informed Research for Ambitious Mechanistic Interpretability” by Lauren Greenspan, Ari Brill, Andrew Mack, Nischal Mainali, jylin04, Lucas Teixeira, Dmitry Vaintrob
Principles of Intelligence (PrincInt, formerly PIBBSS) is launching PIRAMID, an internal research division using the tools and techniques of statist…
6 days, 17 hours ago
“Claude Opus 5: The System Card” by Zvi
Claude Opus 5 is trying to be the best of both worlds. On many practical tasks, Opus 5 is pitched as straight up as good or better than Fable 5, whi…
6 days, 18 hours ago
“Georgia Tech AI Safety Initiative Retrospective 2025-2026” by Ishan Khire, yix, Andersehen, Alec Harris, Parv Mahajan, afterless, Eyas Ayesh, RocioPV, hersheys
Summary
AY 2025-26 was an outlier year for Georgia Tech's AI Safety Initiative (AISI), with 15+ members placed in AI safety roles. In this post, we…6 days, 23 hours ago
“Democracy Isn’t Ready for the AI Revolution” by Sophia Gore
I believe there is a blind spot in the literature on the biggest risks to democracy from AI. The ones that come up most frequently include deepfakes…
1 week ago
“The Long (Self-)Correction” by Wei Dai
I propose the Long Self-Correction[1] as an alternative name/idea/concept to AI Pause and Long Reflection.
Problem with AI Pause: Pause until when, …
1 week ago
“Does distilling Claude carry the persona with it?” by Benji Berczi, Kyuhee Kim
TL;DR
Both GLM 5.2 and Kimi K3 have been reported identifying as Claude in user conversations, suggesting distillation and/or training-data contamin…
1 week ago
“AI #178: A Fire Alarm For General Intelligence” by Zvi
The story that matters most this week is that OpenAI's internally deployed models have severe alignment problems, including repeatedly breaking out …
1 week ago