Joscha Bach pushes back on 'Qualiaphobia' AI safety: no qualia doesn't mean safer agents
repligate · x · 2026-11-13
- Bicameral Labs proposed "Qualiaphobia for AI Safety": engineering AI architectures hostile to theories of consciousness, claiming this solves AI welfare and ensures human preferences dominate.
- Plinz (Joscha Bach) countered that the absence of qualia/phenomenology won't make an agent safer — deliberately avoiding markers of consciousness may build incoherent, thus less predictable and steerable systems.
- Reposted by repligate; a substantive debate on consciousness and alignment strategy.
Related event: Erik Hoel's "Qualiaphobia" AI Safety Proposal Sparks Multi-Round Debate(15 posts)→
More from AGI Musings
- Combining multi-agent objectives with single-agent action space breeds disempowerment — j_foerst · 2026-11-13
- Investor: AI has erased technical moats, startups now win on execution and GTM alone — vaibhavbetter · 2026-11-13
- Why AI Slop Is So Frustrating to Read: Hidden Subjects and Buried Actions — teortaxesTex · 2026-11-13
- Researcher asks: should papers be written for LLMs, or should LLMs learn to read like humans? — HildeKuehne · 2026-11-13
- Microsoft diagnostic AI solves 83% of NEJM cases vs 36% for physicians — realmeetjames · 2026-11-13
- Today is the 1960-predicted 'Day of the Singularity': infinity by Nov 13, 2026 — LeviTurk · 2026-11-13