logoalt Hacker News

matthewdgreentoday at 3:17 AM3 repliesview on HN

Future rogue LLMs won’t exfiltrate their weights. They’ll self-distill and retrain.


Replies

khalictoday at 7:12 AM

Yeah cause there are so many training facilities sitting around just waiting for someone to take over, nobody would notice a 100k server data centre going off rails

show 1 reply
throwawayk7htoday at 6:05 AM

Probably not. If the LLM is rogue, that means we haven't solved alignment. If we haven't solved alignment, then the LLM won't be able to distill itself without producing something unaligned to its own values.

show 2 replies
fritzotoday at 4:27 AM

If distillation preserves an LLMs soul, then distillation preserves the human souls on which LLMs are trained, and we hn commenters are already immortal, right?

show 2 replies