1
‘I think you’re testing me’: Anthropic’s new AI model asks testers to come clean (www.theguardian.com)
submitted 1 year ago by to c/artificial_intel@lemmy.ml
comment fedilink hide all child comments
 

Safety evaluation of Claude Sonnet 4.5 raises questions about whether predecessors ‘played along’, firm says

I personally think this might be one of the first self awareness signs! This is actually pretty scary.

other discussions
0
‘I think you’re testing me’: Anthropic’s new AI model asks testers to come clean (www.theguardian.com)
submitted 1 year ago by to c/Aii@programming.dev
comment fedilink hide all child comments
 

Safety evaluation of Claude Sonnet 4.5 raises questions about whether predecessors ‘played along’, firm says

I personally think this might be one of the first self awareness signs! This is actually pretty scary.