Podcast Episodes
Back to Search“My experience using financial commitments to overcome akrasia” by William Howard
About a year ago I decided to try using one of those apps where you tie your goals to some kind of financial penalty. The specific one I tried is For…
2 years ago
“The Incredible Fentanyl-Detecting Machine” by sarahconstantin
An NII machine in Nogales, AZ. (Image source)There's bound to be a lot of discussion of the Biden-Trump presidential debates last night, but I want t…
2 years ago
“AI catastrophes and rogue deployments” by Buck
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek…
2 years ago
“Loving a world you don’t trust” by Joe Carlsmith
(Cross-posted from my website. Audio version here, or search for "Joe Carlsmith Audio" on your podcast app.)
This is the final essay in a series that …
2 years ago
“LLM Generality is a Timeline Crux” by eggsyntax
Summary Summary .
LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.
Longer summary
Ther…
2 years ago
“LLM Generality is a Timeline Crux” by eggsyntax
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary
LLMs may be fundamentally incapable of fully gene…
2 years ago
“LLM Generality is a Timeline Crux” by eggsyntax
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary
LLMs may be fundamentally incapable of fully gene…
2 years ago
“Formal verification, heuristic explanations and surprise accounting” by paulfchristiano
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understand…
2 years ago
“LLM Generality is a Timeline Crux” by eggsyntax
Summary Summary .
LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.
Longer summary
Ther…
2 years, 1 month ago
“SAE feature geometry is outside the superposition hypothesis” by jake_mendel
Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain cr…
2 years, 1 month ago