korrents

On the map

Tap a claim on the ring to put it at the centre.

← Aligning an AI is not impossible in principle; the problem is that it…

8 connected korrents · 7 moments on record from 10 Jun 2022 to 1 Sept 2026.

Everything filed under AI alignment AI alignment In tensionSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Aligning an AI is not impossible in principle; the problem is that it has to be done without the textbook that would make it look easy. Aligning an AI is not impossible inprinciple; the problem is that ithas to be done without the textbookthat would make it look easy. Last stated 4 years ago 10 Jun 2022 · 4 years ago EY Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are In tension: Alignment is no solution to self-sovereign AI, because it is an unsolved problem whose answers cannot be imposed on every AI company on Earth. — tap to centre the map on it Alignment is no solution toself-sovereign AI, because itis an unsolved problem whoseanswers cannot be imposed on… Last stated 6 days ago 1 Sept 2026 · 6 days ago DB Dean W. Ball — holds since 2026-09-01 — tap for who they are Same subject: Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it. — tap to centre the map on it Building AI that can actuallybe trusted is the goal;containing an AI known to bemisaligned is not a substitute… Last stated 2 years ago 24 Jan 2025 · 2 years ago JL Jan Leike — holds since 2025-01-24 — tap for who they are Same subject: The core of the alignment problem is steerability — whether an AI can be reliably steered anywhere at all — which is a different question from whose values it is steered towards. — tap to centre the map on it The core of the alignmentproblem is steerability —whether an AI can be reliablysteered anywhere at all —… Last stated a year ago 3 Apr 2025 · a year ago HT Helen Toner — holds since 2025-04-03 — tap for who they are Same subject: True AI alignment is impossible because obedience and benevolence are fundamentally incompatible goals. — tap to centre the map on it True AI alignment isimpossible because obedienceand benevolence arefundamentally incompatible… Last stated 6 days ago 1 Sept 2026 · 6 days ago NS Noah Smith — holds since 2026-09-01 — tap for who they are Same subject: Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. — tap to centre the map on it Alignment of today's models isgoing well enough to looksolvable, while aligningmodels we can no longer… Last stated 7 months ago 22 Jan 2026 · 7 months ago JL Jan Leike — holds since 2026-01-22 — tap for who they are Same subject: OpenAI's approach to fixing its AI alignment problems is fatally flawed and misdirected. — tap to centre the map on it OpenAI's approach to fixingits AI alignment problems isfatally flawed andmisdirected. Last stated 6 days ago 1 Sept 2026 · 6 days ago ZM Zvi Mowshowitz — holds since 2026-09-01 — tap for who they are Same subject: There is no route to AI alignment or safety that goes around reliability: a system that cannot reliably follow a known algorithm cannot be made safe. — tap to centre the map on it There is no route to AIalignment or safety that goesaround reliability: a systemthat cannot reliably follow a… Last stated a year ago 7 Jun 2025 · a year ago GM Gary Marcus — holds since 2025-06-07 — tap for who they are Same subject: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. — tap to centre the map on it Very capable AI will be harderto align than current systems,because the loop of spotting abad behaviour and patching the… Last stated 4 weeks ago 11 Aug 2026 · 4 weeks ago RG Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
in tensionsame subject or similar wordingshaded: claims sharing a subjectbar: how recently it was last stated — full and dark this week, a faint sliver at five years

At the centre Aligning an AI is not impossible in principle; the problem is that it has to be done without the textbook that would make it look easy. Last stated 10 Jun 2022 · 4 years ago Holds Eliezer Yudkowsky Read this korrent →