Models already generalise substantially from tasks that can be verified to tasks that cannot.

Added to korrents 13 Feb 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.

• RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. DADario Amodei13 Feb 2026similar wording
• Reasoning will generalize the way instruction tuning did: add enough verifiable domains and, at some point nobody can yet locate, the rest start working on their own. NLNathan Lambert3 Feb 2025similar wording
• Large language models are generalisations of what we already have; the breakthrough that would let AI discover things is still waiting to happen. LRLisa Randall3 Dec 2023similar wording
• The way to find what a model can do is to hand it tasks slightly harder than you believe it can handle. BCBoris Cherny27 Jul 2026similar wording
• Deep learning generalises badly, and catastrophic interference with what a network already knew is the proof of it. RSRichard Sutton26 Sept 2025similar wording

See this on the map →