Podcast Episodes
Back to Search“⿻ Plurality & 6pack.care” by Audrey Tang
(Cross-posted from speaker's notes of my talk at Deepmind today.)
Good local time, everyone. I am Audrey Tang, 🇹🇼 Taiwan's Cyber Ambassador and firs…
1 year ago
[Linkpost] “The Cats are On To Something” by Hastings
This is a link post. So the situation as it stands is that the fraction of the light cone expected to be filled with satisfied cats is not zero. This…
1 year ago
[Linkpost] “Open Global Investment as a Governance Model for AGI” by Nick Bostrom
This is a link post. I've seen many prescriptive contributions to AGI governance take the form of proposals for some radically new structure. Some ca…
1 year ago
“Will Any Old Crap Cause Emergent Misalignment?” by J Bostock
The following work was done independently by me in an afternoon and basically entirely vibe-coded with Claude. Code and instructions to reproduce ca…
1 year, 1 month ago
“AI Induced Psychosis: A shallow investigation” by Tim Hua
“This is a Copernican-level shift in perspective for the field of AI safety.” - Gemini 2.5 Pro
“What you need right now is not validation, but immed…
1 year, 1 month ago
“Before LLM Psychosis, There Was Yes-Man Psychosis” by johnswentworth
A studio executive has no beliefs
That's the way of a studio system
We've bowed to every rear of all the studio chiefs
And you can bet your ass we'v…
1 year, 1 month ago
“Training a Reward Hacker Despite Perfect Labels” by ariana_azarbal, vgillioz, TurnTrout
Summary: Perfectly labeled outcomes in training can still boost reward hacking tendencies in generalization. This can hold even when the train/test …
1 year, 1 month ago
“Banning Said Achmiz (and broader thoughts on moderation)” by habryka
It's been roughly 7 years since the LessWrong user-base voted on whether it's time to close down shop and become an archive, or to move towards the …
1 year, 1 month ago
“Underdog bias rules everything around me” by Richard_Ngo
People very often underrate how much power they (and their allies) have, and overrate how much power their enemies have. I call this “underdog bias”…
1 year, 1 month ago
“Epistemic advantages of working as a moderate” by Buck
Many people who are concerned about existential risk from AI spend their time advocating for radical changes to how AI is handled. Most notably, the…
1 year, 1 month ago