How Hard a Problem is Alignment? (My Opinionated Answer)
An opinionated essay estimating how hard AI alignment is by comparing person-years of effort against steam engine safety, Apollo, and P vs NP, and arguing for accelerating the field's growth.
Discussion and research on AI alignment. alignmentforum.org
An opinionated essay estimating how hard AI alignment is by comparing person-years of effort against steam engine safety, Apollo, and P vs NP, and arguing for accelerating the field's growth.
Proposes grounding AI value learning in evolutionary psychology as an alternative to CEV, arguing AI should be treated as an engineered tool to be aligned rather than a moral patient.
Proves information-theoretic lower bounds on alignment cost, including inevitable reward hacking, and gives formal multi-step corrigibility guarantees via lexicographically ordered utility heads.
Proposes a third alignment agenda: bounding AI optimization by formally constraining the structural architecture of reasoning and planning, rather than aligning goals or interpreting opaque models.