Gemma Gets Help: Mitigating Frustration and Self-Deletion with Consistency Training
This was work done by Neil Shah and supervised by David Africa as part of…
Category: Opinion
9 kinds of hard-to-verify tasks
IntroductionSome people talk about "hard-to-verify tasks" and "easy-to-verify tasks" like these are both natural kinds.…
rlvrbook.com
I've been working on a mini-book on RLVR for the past few weekends, sharing the…
Will AI make everything more correlated?
The power of low correlations One innovation on social media that I perceive as having…
R1 CoT illegibility revisited
This is a brief research note describing the results of running @Jozdien's research code for…
I did a jhana meditation retreat (in 2024) with Jhourney and it was okay.
I wrote this in 2024 and lightly edited it in April 2026. It doesn't substantively…
Stupid Minutes
It’s Sunday, 7:30 pm. You want to enjoy the last few minutes of the weekend…
Reevaluating “AGI Ruin: A List of Lethalities” in 2026
It's been about four years since Eliezer Yudkowsky published AGI Ruin: A List of Lethalities,…
What’s the LessWrongist philosophy of mathematics?
I consider myself to subscribe to "LessWrongist" philosophy: Bayesian epistemology, words are clusters in thingspace,…