Self-promo
A skeptical take on Anthropic’s AI introspection experiment
A post invites questions at COLM during the week of October 5 about whether AI models can examine their own computations.
TLDR
A post argues that whether AI models can introspect on their own computations matters to debates about ethics, consciousness and possibly God. It invites people at COLM during the week of October 5, 2026, to ask about a skeptical take on Anthropic’s introspection experiment.
Combined views
185
1 Source, first seen ago
