Fable #6: The Return of the King
The blip is over. We have Fable back. Utah teapot: happy fable/mythos easter Wednesday, to those who celebrate Here is the official letter restoring Fable, great…
Latest
June-July 2026 AI Security via Formal Methods
Last month, I said I would do a bigger writeup of Nora’s funding call. I did not. But she is hiring currently, and I want you…
Scheming Evals Mislead in Both Directions
We spent several weeks measuring in-context scheming, the behavior where a model covertly pursues a misaligned goal while outwardly appearing to comply, and the result that…
Fragile Correctness: Cases of reasoning harming performance
Sometimes a reasoning model appears to pass through the correct answer before ending up wrongMotivationFigure 1: From the Opus 4.8 system card (page 196)Figure 1 shows…
One axis and two features, how I solved the first puzzle from BlueDot and how a classifier hid country on the food direction
In this post I walk through the first Technical AI Safety puzzle from BlueDot and why linear probes would have missed all the most interesting stuff.In…
The Case for AI Behavioral Science
This is NOT an anthropomorphizing case.It is my view that AI research is, at the moment, split between three camps:Model-internal research (mechinterp folks)Capability research (METR, Irregular,…
Lydia Laurenson: "The Inside Story of Leverage Research"
Lydia Laurenson recently posted an article called "The Inside Story of Leverage Research" that gets into substantially more detail on what went on in that organization…
When Role-playing, Do Models Believe What They Say?
TL;DRWhen a model role-plays a persona, does it only change what it says, or also what it internally represents as true?To study this, we induce personas…
You Should Choose How You React to Your Feelings
One of the things I love about parenting is being frequently reminded how many things are not the default for most people. While I see this…
I can't think of great interventions for ensuring third-party model access.
SummaryI'm increasingly convinced that model access parity is a big deal and we are not on track to achieve it. By model access parity, I mean…