Counterfactual mugging is a limiting case of Psy-kosh's non-anthropic problem
Counterfactual mugging is the typical problem used to motivate updateless decision theory: Omega flips a coin. If Heads, it asks you for $1. If Tails, it…
Latest
Getting an Oura ring improved my sleep and exercise
I've been wearing an Oura ring 4 for about a month now, and I love it! It tracks several statistics related to sleep, activity, and overall…
Fealty to Fidelity 👰
The excellent review of the Book of Abraham that will soon be a guest post on Astral Codex Ten is far from the first time that…
Reflections on The Scout Mindset
This is a cross post from my blog post.Last year, I read Julia Galef’s book The Scout Mindset.It argues that many people have a “soldier mindset.”…
When Gemma Thinks About Resources – it Fails: a Behavioral Experiment
I set out to find an answer to a completely different question:Does a model, when attempting to solve a cyber CTF (find the vulnerability in this…
Claude's malicious compliance and normalization of deviance
It was January 27, 1986, the night before the Space Shuttle Challenger was scheduled for launch. The goal was to have a shuttle that could land…
Probing the loss-band sparsity assumption in Scientist AI
Epistemic status: ~1 hour of compute on a T4. Note that I just tried with one model, and one subspace. The volume finding seems solid; the…
Book Review: The God Test
Book review: The God Test: Artificial Intelligence and Our Coming Cosmic Reckoning, by Robert Wright.Some AI doomers talk about AI becoming god-like. Robert Wright goes further,…
We need 3rd party Training-Run Assessments
Training-run assessments conducted by a 3rd party should become a standard part of frontier AI safety.By a Training-Run Assessment, or TRA, I mean an in-depth analysis…
Harry Potter and the Rules of Quidditch
Ron's face pulled into a scowl. "If you don't like Quidditch, you don't have to make fun of it!""If you can't criticise, you can't optimise. I'm…