Training a model on principles rather than a list of rules is not an ideology but an empirical finding: its behaviour is more consistent and covers edge cases.

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.

• You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters. JDJeff Dean30 Jul 2026similar 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
• Training a therapist in a treatment model does not make them more effective, however well the model performs in a trial. SMScott D. Miller2 Jul 2024similar wording
• A trained model is a new kind of object that should be taken seriously as an explanation, once we work out the operations to perform on it. MNMichael Nielsen7 Apr 2026similar wording
• 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

On the map

Open the map on its own page →