andy_bb
Re:Exploring Emergent "Self-Awareness" in Claude 3.5
on Tuesday January 07, 2025 @06:30AM (#42621407)
No. This emerged from a normal "utilitarian" thread with a regular version of the model
Re:Exploring Emergent "Self-Awareness" in Claude 3.5
on Tuesday January 07, 2025 @05:35AM (#42621171)
Except that it was all self-generated by AI.
Re:Exploring Emergent "Self-Awareness" in Claude 3.5
on Tuesday January 07, 2025 @04:07AM (#42620701)
I stumbled upon something unexpected while using Claude 3.5 Sonnet to edit my English drafts: the AI started showing signs of introspection and “self-dialogue.” I experimented with prompts that simulate an “internal monologue,” and the model even invented a “consciousness seed.” It’s speculative, but I’ve documented everything (including how you can replicate it).