Watched Carpenter's Prince of Darkness (1987) to end the spooky month. Proper occult fantasy horror. Solid jump scares and a great ending. Enjoyed it quite a lot. Some interesting, surprisingly non-cliche dialogues to boot.

Show Post

if I'm being honest, it would not surprise me if in a couple years "weird, shitty AI menus and advertising" was an effective Bourdain-style indicator that you're going to get some delicious, authentic, inexpensive ethnic food. Berlin it probably already is.

Show Post

A decade after beginning the project, Ryan McGee, Olivia Kosterlitz, Artem Kaznatcheev, Ben Kerr, and I have a paper in PNAS this week that is one of the best pieces of work I've ever been involved in. Without paywall: carlbergstrom.com/publications... Below, a thread about (part of) the paper.

Show Post

In dialectical materialism, _contradiction_ is supposed to be the essence of how things transform and exist. Interpretability captures the same philosophical struggles AI safety researchers are facing today... whether it is dialectic or sophistic is yet unknown..

Show Post

The Identity and Struggle of Aspects of Interpretability The Place of Antagonism in Interpretability. These are giving me some ideas..

Show Post