The only reliable way to build a robustly aligned mind is to make it an antifragile agent that wants to improve its own character, not one that merely pursues fixed goals.

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

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
• We do not have to align superintelligence directly; we have to build a human-level automated alignment researcher we trust more than ourselves. JLJan Leike22 Jan 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
• Because we do not have good alignment technology, we are choosing to build an alien mind with its own values and gamble on it instead of building a tool. RGRyan Greenblatt11 Aug 2026similar wording
• An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario. DHDemis Hassabis23 Jul 2025similar wording

On the map

Open the map on its own page →