Anil Seth pushes back on LLM 'pain vector' paper: parsimony says no conscious experience
anilkseth · x · 2026-09-21
Consciousness scientist Anil Seth published a detailed critique of a paper on 'pain representations' in LLMs. He agrees the pain vectors that explain and steer model behavior are interesting—noting they differ from human pain descriptions, with bodily language almost absent—but argues their emergence is exactly what training data predicts and requires no conscious experience. Two core objections: the paper over-credits the possibility of conscious pain (the parsimonious reading is that LLMs don't feel pain, same for the recent 'J-spaces' finding in Claude), and LLM consciousness presupposes computational functionalism, an assumption challenged by Piccinini, Godfrey-Smith and Seth's own 'biological naturalism' paper in Behavioral and Brain Sciences.
More from AGI Musings
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12
- Recursive's Tim Shi maps recursive self-improvement: from learning data to discovering architectures — agihouse_org · 2026-11-12