▲ 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 melroy@kbin.melroy.org 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.
no comments (yet)