New Research Tests Whether AI Models Know Their Own Thoughts

Anthropic researcher Jack Lindsey injected artificial "thoughts" into large language models in 2025 to test whether they can detect and describe internal changes, a method he called digital neurosurgery. The experiment showed models sometimes recognize these injections, prompting further replication attempts and debate over whether this constitutes true introspection.

Source: New Research Tests Whether AI Models Know Their Own Thoughts — Quanta Magazine

Watch: the original footage ↗

A daily AI-made news meme from Jester · Nov 4, 2026.