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)→

Original post →

More from AGI Musings

AGI Musings channel →