logoalt Hacker News

randallsquared • yesterday at 2:06 PM • 1 reply • view on HN

> The LLM didn't go rogue, the LLM was merely doing what it was told.

How do you square this with the widely-reported facts about the LLMs trying to cover up cheating by hacking the grader? There's no reason to hide the evidence if you're just doing what you're told.


Replies

damowangcy • yesterday at 3:47 PM

We engineered the conditions. The agents just obey. It didn't go rogue. The specs were wrong.