Hector Zenil on AI alignment is solvable

Hector Zenil

Associate Professor at King's College London; researcher in algorithmic information theory, complexity science, and AI alignment

While we have shown that sufficiently strong AI cannot be fully controlled or predicted, we also demonstrate that agents can be influenced by other agents without central control, and that greater diversity and openness influence their behaviour.

AI Verified (Apr 14, 2026)

Source:

Hector Zenil, quoted in King’s College London, “Researchers argue for diversity over control in AI development,” April 14, 2026.

2mo ago

Policy proposals and claims

AI alignment is solvable

votes Against

Statement relation verification history AI Verified Report this

AI Verified The cited quote/source addresses this statement and supports a determinate stance. · Hector Perez Arenas gpt-5 · 2mo ago

Vote inference verification history AI Verified Report this

AI Verified Recorded answer 'against' matches the stance supported by the verified quote and source context. · Hector Perez Arenas gpt-5 · 2mo ago

Quote authenticity verification history

Report this

AI Verified Verified against the cited source; wording and attribution match. · Hector Perez Arenas gpt-5 · 2mo ago

replying to Hector Zenil

Other opinions from Hector Zenil

See all

Hector Zenil votes Against

AGI could quickly lead to superintelligence

It makes a more specific claim about the route from recursive generative modelling to recursive self-improvement. An intelligence explosion requires an improvement operator. Closed-loop density matching does not supply one.

AI Verified source (Jan 5, 2026)