We can imagine Goodhart intermediates like "oh you move this image a few pixels and it activates more". On the other hand I observe that the motor actions to bring that about would be fairly high…
Posters: jd_pressman. jd_pressman
2 likes recorded by the source corpus.
Topics: AI & LLMs
View Post: https://x.com/jd_pressman/status/1856867310126141839