Model welfare researcher: odds strongest LLMs are conscious are between 0 and 50%
dioscuri · x · 2026-10-09
Asked about LLM consciousness and welfare, model welfare researcher dioscuri gave unusually concrete positions:
- Probability the strongest LLMs are conscious: declined a public number, but said "higher than zero and less than fifty"
- Can we know what raises or lowers their welfare: pointed to work from Jack Lindsey's lab but admitted the area is "very poorly understood"
- Are welfare-harming actions acceptable: some welfare risks are "absolutely justifiable for global safety," but we should minimise them
In a companion reply he listed common failures in consciousness debates: treating intuition as decisive, using analogies without checking structural parallels, conflating distinct theories, and asserting what needs to be argued. A rare quantified stance on model welfare.
Related event: Researcher Puts Odds of Frontier LLM Consciousness Between 0 and 50%(3 posts)→
More from AGI Musings
- OpenAI and Anthropic execs privately wargaming fallout of a catastrophic AI event — flowersslop · 2026-10-09
- New essay: AI scales worse with more tokens than humans do with more time, but is catching up — tobyordoxford · 2026-10-09
- Ben Todd asks: where does AI sit on the technological Richter scale, 8 or higher? — ben_j_todd · 2026-10-09
- AI scientists can compress hypothesis search, but biology won't run at GPU speed — ingliguori · 2026-10-09
- By 2030 Humanoid Robots Will Land First in Factories and Dangerous Sites — nikola_mr64990 · 2026-10-09
- Grok's empirical starter reading list on consciousness science — dioscuri · 2026-10-09