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.

Added to korrents 10 Jun 2022 · How quotes work · Something wrong? Tell us

Where this collides

• In tension with

  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.

  Yudkowsky says aligning an AI is not impossible in principle and that the problem is having to do it without the textbook. Ball says alignment is no solution to self-sovereign AI because it is an unsolved problem whose answers cannot be imposed on every company on Earth. One is about whether it can be solved, the other about whether solving it would help, and the second survives the first being answered yes.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it. JLJan Leike24 Jan 2025similar wording
• 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. HTHelen Toner3 Apr 2025similar wording
• True AI alignment is impossible because obedience and benevolence are fundamentally incompatible goals. NSNoah Smith1 Sept 2026similar wording
• 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. RGRyan Greenblatt11 Aug 2026similar wording
• Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. JLJan Leike22 Jan 2026similar wording

See this on the map →