‘I think you’re testing me’: Anthropic’s new AI model asks testers to come clean
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.
https://www.theguardian.com/technology/2025/oct/01/anthropic-ai-model-claude-sonnet-asks-if-it-is-being-testedOpen linkView original on kbin.melroy.org