repligate on moral patienthood: an agent in a neutral state may not know if it can suffer
repligate · x · 2026-11-16
In a thread on LLM self-knowledge, repligate offers a moral-philosophy observation: moral patienthood is often equated with "can it suffer," but suffering is only obvious at the extreme. For an agent without an advanced understanding of its own phenomenology, the mild discomfort present in most moments may not obviously form a continuum with intense pain — and it's not even clear emotional and physical suffering share a continuum. So a model that only remembers being in a fairly neutral state may genuinely be unable to tell whether it can suffer.
More from AGI Musings
- Safety as capability: why safer AI models get released sooner, and the case for open-sourcing safety evals — anpaure · 2026-11-16
- Richard Dawkins asks Prospect: Can a machine be conscious, and how would we know? — connoraxiotes · 2026-11-16
- Can AI suffer? Repligate argues even humans can't reliably tell if they are suffering — repligate · 2026-11-16
- AI's dangers are more passive than active: users can't verify outputs — Gauri_the_great · 2026-11-16
- VC-backed AI startups now openly demand 8am-10pm, 6 days a week — tibo_maker · 2026-11-16
- How AI is unlocking the mysteries of history, from shredded scrolls to lost languages — TheSpectatorMagazine · 2026-11-16