Podcast Episodes
Back to Search“Frontier AI Models Still Fail at Basic Physical Tasks: A Manufacturing Case Study” by Adam Karvonen
Dario Amodei, CEO of Anthropic, recently worried about a world where only 30% of jobs become automated, leading to class tensions between the automa…
10 months, 2 weeks ago
“Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update #2)” by Neel Nanda, lewis smith, Senthooran Rajamanoharan, Arthur Conmy, Callum McDougall, Tom Lieberum, János Kramár, Rohin Shah
Audio note: this article contains 31 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in th…
10 months, 2 weeks ago
[Linkpost] “Playing in the Creek” by Hastings
This is a link post. When I was a really small kid, one of my favorite activities was to try and dam up the creek in my backyard. I would carefully m…
10 months, 2 weeks ago
“Thoughts on AI 2027” by Max Harms
This is part of the MIRI Single Author Series. Pieces in this series represent the beliefs and opinions of their named authors, and do not claim to …
10 months, 2 weeks ago
“Short Timelines don’t Devalue Long Horizon Research” by Vladimir_Nesov
Short AI takeoff timelines seem to leave no time for some lines of alignment research to become impactful. But any research rebalances the mix of cu…
10 months, 3 weeks ago
“Alignment Faking Revisited: Improved Classifiers and Open Source Extensions” by John Hughes, abhayesian, Akbir Khan, Fabien Roger
In this post, we present a replication and extension of an alignment faking model organism:
Replication: We replicate the alignment faking (AF) pap…
10 months, 3 weeks ago
“METR: Measuring AI Ability to Complete Long Tasks” by Zach Stein-Perlman
Summary: We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been consistently …
10 months, 3 weeks ago
“Why Have Sentence Lengths Decreased?” by Arjun Panickssery
“In the loveliest town of all, where the houses were white and high and the elms trees were green and higher than the houses, where the front yards …
10 months, 3 weeks ago
“AI 2027: What Superintelligence Looks Like” by Daniel Kokotajlo, Thomas Larsen, elifland, Scott Alexander, Jonas V, romeo
In 2021 I wrote what became my most popular blog post: What 2026 Looks Like. I intended to keep writing predictions all the way to AGI and beyond, b…
10 months, 3 weeks ago
“OpenAI #12: Battle of the Board Redux” by Zvi
Back when the OpenAI board attempted and failed to fire Sam Altman, we faced a highly hostile information environment. The battle was fought largely …
10 months, 3 weeks ago