MIRI responds to critics: modern ML doesn't dent the difficulty of aligning ASI
robbensinger · x · 2026-09-14
Rob Bensinger (MIRI) summarizes the core disagreement with critics who argue modern ML is unusual and might accidentally produce human-friendly ASI. MIRI's response: modern ML looks more dire in some ways and less in others, but overall doesn't materially dent the background difficulty of alignment, reiterating that ASI built with modern ML this decade is very unlikely to love us and promote human flourishing.
Related event: MIRI Researcher and Alignment Researcher Clash Over ASI Doom Arguments(7 posts)→
More from AGI Musings
- Yoav Goldberg translates AI industry speak: 'third-party evaluators' are spies, 'pacing' means stop spending — yoavgo · 2026-09-14
- Melanie Mitchell's New Essay Dissects Misleading AI Metaphors and Real Risks — mmitchell_ai · 2026-09-14
- zetalyrae: true atheists are rare — people find teleology everywhere, even thermodynamics — zetalyrae · 2026-09-14
- Humans got better at chess and Go after AI dominance — and math may see the same effect — RexDouglass · 2026-09-14
- Commenters Misread Dario's Letter: He Never Said 'No More Big Models' — menhguin · 2026-09-14
- Pundits Screamed 'Communism' Over a Short Letter They Barely Read — menhguin · 2026-09-14