New Anthropic Study: Emergent Introspective Awareness

Glitchy black and white screen, computer code, text reading words, pixelated effects, glitch art, dark background.

Scientists Found Evidence That Claude Can Sometimes Introspect—And It’s More Complicated Than It Sounds On October 29, 2025, Anthropic researchers published something unusual: evidence that their AI model, Claude Opus 4 and 4.1, possesses a limited but genuine form of introspection. Not the kind where Claude claims to know what it’s thinking—it does that all […]