logoalt Hacker News

sambejk • today at 8:34 AM • 1 reply • view on HN

It feels like we have overfitted on safety by a long mile. This is how labs that care less about safety (a.k.a. Chinese & Grok) will probably be able to catch up in the future.


Replies

notrealyme123 • today at 1:25 PM

A few weeks ago that companies agent hacked another company to solve a task by whatever means possible. Where exactly are they overfitting for Safety here?

➕ show 1 reply