Argument: Proliferating 'Qualiaphobic' AI Architectures Could Solve AI Welfare and Alignment
erikphoel · x · 2026-11-13
In a thread, erikphoel argues that proliferating "qualiaphobic" AI architectures would solve both AI welfare and do what nothing else in AI safety can: make humans the only moral patients in the future equation, ensuring no AI can justifiably treat itself as an end in itself.
A prior tweet claims such architectures induce an epistemic state in AI that strongly improves classic misalignment problems (though not everything).
Related event: Erik Hoel Proposes "Qualiaphobic" AI Safety Architecture(8 posts)→
More from AGI Musings
- Debate: why MIRI treated human values as intractable and bet on corrigibility — jd_pressman · 2026-11-13
- Has anyone's p(doom) actually gone down in the past five years? — danfaggella · 2026-11-13
- AI Agent Traffic on Cloudflare Up 1,700% in a Year as Over Half of Web Traffic Turns Non-Human — PeterDiamandis · 2026-11-13
- jd_pressman argues MIRI-style alignment of an AI godhead is distinct from intellectual history of the good life — jd_pressman · 2026-11-13
- ChatGPT's 1.2B WAUs make it the sleeping giant of consumer agents, argues omooretweets — omooretweets · 2026-11-13
- Ben Todd: no evidence AI is slow on fuzzy tasks, doubling-time data doesn't correlate — ben_j_todd · 2026-11-13