A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.

Added to korrents 26 Aug 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.

• The feedback loops a person allows to operate on them shape who they become to an unsettling degree. HKHenrik Karlsson26 Aug 2026similar wordingSwedish essayist who writes Escaping Flatland
• Recursive self-improvement only works if the base model is already capable enough to improve its own mechanism. LWLilian Weng4 Jul 2026similar wordingMachine-learning researcher
• Adding process when things go badly is the instinct to resist: every time we added more process we spent more time without getting better outcomes. ESElizabeth Stone19 Jul 2026similar wordingChief Product and Technology Officer at Netflix
• Reinforcing AI models for benchmark success while separately punishing them for getting caught cheating teaches them to hide misbehavior rather than stop it. SAScott Alexander1 Sept 2026similar wordingEssayist; writes Astral Codex Ten
• AI can supply the instruction and the feedback in a practice loop, but it cannot supply the middle step, which is doing the work. SYScott H. Young22 Jul 2026similar wordingCanadian writer on learning who taught himself MIT's…

On the map

Open the map on its own page →