Latest updates · 21 October 2026
In the full issue →Can we look for consciousness inside a language model? An Economist feature examines Anthropic's experiments that peer into a model's layers while it is asked to introspect.
Research, industry & policy
- The search for consciousness inside LLMs, Mint (The Economist) · 20 Oct 2026: The piece describes an experiment in which researchers watched Claude Sonnet 4.5's internal activity while asking it to count to five and 'introspect deeply'.
Conferences, workshops & events
- CIFAR Neuroscience of Consciousness Winter School, 3–5 Dec 2026 · Cape Town (University of Cape Town): CIFAR winter school.
Why it matters
Interpretability tools are turning questions about machine consciousness from pure philosophy into testable claims.
