A thread through the archive
Essays tagged “mechanistic interpretability”. Follow an idea across the archive.
Scott explains current mechanistic interpretability techniques for understanding AI cognition, from linear probes to emotion vectors, showing they're useful for monitoring but insufficient for controlling AI behavior or ensuring safety.
Scott argues that dismissing AI as 'just a next-token predictor' is like dismissing humans as 'just reproduction machines' - both confuse the optimization process that shaped an entity with how that entity actually thinks.
Scott reviews a paper by leading researchers attempting to determine AI consciousness through computational theories, critiques their conflation of access and phenomenal consciousness, and predicts society will inconsistently ascribe consciousness to AIs based on their social roles rather than their underlying architecture.