zetalyrae: alignment debates assume ASI can 'enumerate the real numbers'
zetalyrae · x · 2026-10-29
Researcher zetalyrae argues that many AI alignment arguments quietly reduce to assuming "ASI can enumerate the real numbers" — that is, presuming an aligned superintelligence can solve any arbitrary problem without first investigating whether the problem is solvable in principle.
His point: alignment discussions should start by establishing whether a target problem admits a solution at all, before debating whether a superintelligence could implement it.
More from AGI Musings
- Millions of tweets, zero scenarios Shulman and Bostrom didn't already think through — abhiadesai · 2026-10-29
- AI Software Factory vs Dark Factory: two stages of autonomous software delivery — Pavan_Belagatti · 2026-10-29
- Is Google's claimed use of RSI the start of the singularity under Vinge's and Good's definitions? — Extraaltodeus · 2026-10-29
- 'AI is just a tool' misses the point: writing and print reshaped humans too — YogeshMalik · 2026-10-29
- Why a multibillion-dollar law firm can go bankrupt: lawyer friends explain the economics — NathanpmYoung · 2026-10-29
- Dating app Rivet shows voters AI-blended faces of matches, making facial ranking bias visible — organic_ta6 · 2026-10-29