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.
Related event: The Anthropomorphizing AI Debate: Useful Tool or Public Misinformation(20 posts)→
More from AGI Musings
- Autonomous AI Viruses Will Be a Manageable Nuisance, Not an Existential Threat — binarybits · 2026-08-31
- Stop anthropomorphizing AIs unless you stop anthropomorphizing humans — TheZvi · 2026-08-31
- LLMs as addiction exponents amplifying desires like a casino — StewartalsopIII · 2026-08-31
- View: Conceptual learning requires strong intrinsic motivation — imjuhokim · 2026-08-31
- Discussion on AI learning bottleneck: lack of real-world verification — imjuhokim · 2026-08-31
- Perspective on anthropomorphizing LLM actions — JacquesThibs · 2026-08-31