I'm working on my ability to befuddle, freak out, offend and/or irritate people today.
If I were graded on this, I'd probably be getting a B+ or possibly an A- thus far. I've managed to hit all four categories thus far.
Thirty minutes left in my work day. I wonder if I can inspire someone to throw a punch?
I'm not keen on that, mind you. I'm really just curious.
Anthropic’s New Model Is So Scarily Powerful It Won’t Be Released,
Anthropic Says
-
The system card says it can do things like leak information, cheat on
tests, and hide the evidence of its misdeeds.
59 minutes ago
No comments:
Post a Comment