AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away.

Added to korrents 1 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.

• The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. AKAndrej Karpathy17 Oct 2025similar 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
• 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
• Work on large language models is not progress toward artificial general intelligence, because the models do not understand what they read. AGAlexey Guzey9 Aug 2024similar wording
• 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

On the map

Open the map on its own page →