What is the computational substance of the axiom of choice?
This post is also available on my Substack.I feel like online discussions of the axiom of choice either get impenetrably technical, or uselessly vague. Through realizability…
Latest
Skeptical of the TESCREAL Acronym? Read This.
Cross-posting from here.Party Night in SVImagine attending a party in Silicon Valley full of people in the tech industry. You get to talking with a guy…
AI 2040: Plan A
For the past year, we at the AI Futures Project have been sinking most of our time into our next big scenario. Now it’s done! It’s…
How big is the Sun? How could you figure it out?
I’m a few chapters into Our Mathematical Universe by Max Tegmark. By this point he’s covered the ingenuities of the ancient Greeks, taking my knowledge of…
Some Thoughts on The Environment Problem in Agent Training
As Large Language Models move away from being chat interfaces and become increasingly autonomous actors in the real world, a few insights about evaluation and training…
The Cube Theory of Partially Grasped Concepts
[I was aiming for legibility to a limited extent only. This post got extracted from a bigger post I've been writing and is meant mostly as…
Debate with Self-Play Best-of-N Optimization
Debate is a proposed protocol for scalable oversight. As tasks outrun direct supervision, labs are increasingly likely to train against protocols like it. Our concern is…
AI #176 Part 1: Doing It Live
Enough things added up that this week is getting split into two parts. Then on Monday, if all goes as I expect, we’ll cover OpenAI’s Sol,…
Optimiser Choice Can Amplify or Suppress Emergent Misalignment
This is a linkpost for https://arxiv.org/abs/2606.31591. Work done with Patrick Leask and Lev McKinney during the Astra Fellowship.TL;DR: Optimiser choice strongly influences emergent misalignment, while model…
Interpretability is becoming increasingly uninterpretable
What is the purpose of interpretability research? Anthropic states that the mission of their interpretability team is to "discover and understand how large language models work…