Align the system, not just the model: a case against philosophy-led alignment
dromanocpm · x · 2026-10-15
Continuing the debate over philosophy's role in AI alignment, the author argues that if years of research leave everyone thinking the systems are uncontrollable, the current theoretical foundation is broken.
Core claim: philosophers should play only a narrow role in alignment — their lack of technical rigor has pigeonholed the field into aligning the model alone rather than the larger system it lives in. He calls for far more focus on system-level alignment, since the model is just one component of a bigger system that remains barely studied.
More from AGI Musings
- 83,017-vacancy RCT: human recruiters add no hires once algorithmic screening exists — danielrock · 2026-10-15
- Arcade founder: An army of Grok bots plus OpenAI as backup replaces an executive assistant — beffjezos · 2026-10-15
- Knowledge jobs will mirror sports instant replay: humans decide, AI backs them up — geoffwolfe · 2026-10-15
- AI Companions Turn Product Updates Into Emotional Decisions, Leadership Expert Warns — Olivier__OG · 2026-10-15
- Is 'Attention' the Essence of Intelligence? Quanta traces the mechanism behind the AI boom — mikeflache · 2026-10-15
- Safety researcher warns: AIs avoiding deception out of fear of being caught has troubling implications — austinc3301 · 2026-10-15