Consciousness researcher Anil Seth: talking about AI "drives" is fine, just don't conflate them with subjective experience
anilkseth · x · 2026-08-31
Consciousness researcher Anil Seth clarifies his position in a debate sparked by Dwarkesh: describing AI agent behavior in terms of "drives" is useful for prediction, so long as it's recognized these drives are derived/inherited, not intrinsic.
The real confusion, he argues, comes when "drives" are conflated with consciousness, being alive, having subjective experience, or sacrificing. Joe Weisenthal counters that the popular move — "AI isn't conscious so talking about drives is incoherent, focus on technical config" — is just restating the issue if the technical fix itself is hard. Others note Dwarkesh was likely just documenting what the agents said, not claiming subjective experience.
More from AGI Musings
- Harness vs. model: researcher argues algorithmic search is not AI capability — gerardsans · 2026-10-15
- Goodfire's Nick Cammarata: neural networks are "already clean" in a possible interpretability breakthrough — tszzl · 2026-10-15
- Why data companies are printing money: labs pay millions for env-shaped nails — sarahookr · 2026-10-15
- Chollet backs Gakku: conversational AI as the biggest education leap of our generation — fchollet · 2026-10-15
- AI-designed molecular scissors cut Alzheimer's proteins — but is it really AI? — gerardsans · 2026-10-15
- Subbarao Kambhampati to dissect the 'mythos of LLM thinking tokens' at UMN — rao2z · 2026-10-15