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.
More from AGI Musings
- Five agents can agree because they made the same mistake, krishnan warns with satire — krishnan · 2026-10-31
- Google's earnings offer clearest look yet at the cruel economics of AI search — dinabass · 2026-10-31
- Stanford 12-month study of 439 users: heavy AI companion use sticks, well-being drops via less human contact — stanfordnlp · 2026-10-31
- Wired AI Lab: Codex tried to bench Erling Haaland in a fantasy football experiment — willknight · 2026-10-31
- a16z: B300 GPU rentals up 106% since July while average token prices fall 58% — a16z · 2026-10-31
- Stanford's TaskNet builds occupational task inventories from worker interviews at scale — stanfordnlp · 2026-10-31