Juan Benet asks if valuing diversity of consciousness follows from knowledge growth

juanbenet · x · 2026-09-30

Protocol Labs founder Juan Benet engaged with an AI alignment article's principles, questioning whether principle 3 (valuing diversity of consciousnesses) can be derived from principle 1 (growth of knowledge) — a proof would tie into the orthogonality thesis and reduce many risks. He frames it as finding an attractor basin in capabilities/goals space where capability increases stay within a goal subspace, noting it requires agent architectures where knowledge can affect values, as in humans and current LLMs.

Original post →

More from AGI Musings

AGI Musings channel →