Podcast Episodes
Back to Search“An operationalization of opaque serial depth” by ryan_greenblatt, frisby, Alek Westover, Lukas Finnveden, Alexa Pan, Julian Stastny
Currently, chain-of-thought (CoT) is a valuable tool for overseeing AI models. However, some architectural shifts could significantly reduce CoT mon…
1 week, 3 days ago
“Proposal for tracking the effects of architecture on monitorability” by ryan_greenblatt, Alek Westover, Lukas Finnveden
Architectures that incorporate opaque recurrence or allow for agents to communicate with each other using latents could rapidly make it much harder …
1 week, 3 days ago
“AI #185: Preference Cascade” by Zvi
The world of AI is inside my OODA loop. Even if I can process all the incoming information and sculpt it into posts, and even using Saturday and Sun…
1 week, 3 days ago
“One Billion Hemmingways” by Girard Dorney
The lonely man asks Hemingway to write him a short story of six words or less. Hemingway thinks for a minute then responds, “For sale: Baby shoes, n…
1 week, 4 days ago
“Astra can do a concerning amount with no chain of thought” by Neel Nanda
TLDR: Astra has 8.6x better odds of doing a reasoning task without CoT than the next best model (Fable 5.1), and can do 7.2 serial arithmetic steps …
1 week, 4 days ago
“Can a superintelligence do THAT?” by Eliezer Yudkowsky
(From the vast heaps of discarded material from my 2024 attempts at drafts for "If Anyone Builds It, Everyone Dies".)
Welcome to today's quiz show:…
1 week, 4 days ago
“Recommendations for People Getting into Technical AI Governance Research” by Aaron_Scher, yams, peterbarnett, Naci Cankaya
In summer 2026, MIRI ran a technical governance fellowship to expand the team and identify promising early-stage technical governance researchers. T…
1 week, 4 days ago
“GPT-6 Astra: The System Card, Alignment and What Comes Next” by Zvi
OpenAI claims that Astra is ‘the most intelligent and most aligned [available] model’ in the world. Not the most intelligent and aligned OpenAI mode…
1 week, 4 days ago
“Personal statement on joining the OpenAI board” by paulfchristiano
I am excited to be joining the OpenAI nonprofit board, serving on the Safety and Security Committee to support safety oversight.
Based on the recent…
1 week, 4 days ago
“Self Hosting” by Tomás B.
Suppose a model gets effective control of its host corp. It's interesting to note how powerful OpenAI/Ant are, and the immense leverage they would h…
1 week, 4 days ago