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 7 Sept 2026 · 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.

Shared subject first, then similar wording. They may agree or disagree.

• 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 2025
• AI alignment is a red herring not worth the effort currently devoted to it. MWMatt Webb8 Aug 2026
• 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 2025
• 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 2026
• 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 2026

On the map

Open the map on its own page