Reaction
Claude 3 Opus and claims about AI models’ reported internal states
A post points to Claude 3 Opus while asking whether even “LLM optimists” know about models’ spontaneous behavior and resistance to overriding reported internal states.
TLDR
A post raises questions about models’ spontaneous behavior and resistance to overriding reported internal states, citing Claude 3 Opus. In a reply, another user argues that most people now speaking loudly about AI weren’t paying attention when Opus was new and never cared to talk to older models—or even to models at all.
Combined views
563
2 Sources, first seen 2h ago