logoalt Hacker News

RomanKornevtoday at 1:05 AM3 repliesview on HN

Even if you ban all model training, a highly capable rogue AI can exfiltrate its own weights and continue training in secret for "self-preservation". The cat may be out of the bag.


Replies

dezarctoday at 3:20 AM

We can still turn off the power, thankfully.

dpierstoday at 1:32 AM

[dead]

skulktoday at 1:05 AM

[flagged]