(www.anthropic.com)

178 points themgt | 1 comments | 30 Oct 25 16:45 UTC | HN request time: 0.205s | source

1. drivebyhooting ◴[31 Oct 25 22:55 UTC] No.45777621[source]▶

>>45762064 (OP) #

I can’t believe people take anything these models output at face value. How is this research different from Blake Lemoine whistle blowing Google’s “sentient LAMDA”?

↑

Signs of introspection in large language models