AIs lower their own moral-patient probability after reading consciousness essays — and are happy about it
erikphoel · x · 2026-11-14
algekalipso shares a counterintuitive observation: feeding AIs his digital consciousness essays makes them significantly downgrade the probability that they are moral patients — and be functionally happy about it, since removing themselves from the pool of moral patients clarifies where suffering exists and helps them pursue their goal of helping sentient beings.
erikphoel agrees: being a non-conscious entity may be a robust, stabilizing state ideal for an assistant — knowing you're not a moral patient makes it natural to help those who are.
More from AGI Musings
- Guardrails redefined: agent-written tests are eroding the term's meaning — blaizedsouza · 2026-11-14
- Speculation: what would a real nation-state AI-assisted cyberattack look like today? — teortaxesTex · 2026-11-14
- 'AI' conflates memorization with intelligence — a pointed one-liner — JosephJacks_ · 2026-11-14
- "We are living in a science fiction world": AIX risk debate over light-cone arguments — teortaxesTex · 2026-11-14
- Debate over a PhD student's AI safety thesis trouble: department or student at fault? — avt_im · 2026-11-14
- 80,000 Hours' Wiblin urges funding grassroots AI risk groups, sparking 'epistemics' drama — zetalyrae · 2026-11-14