factual
System prompt as cheap, fast behavior patch
The system prompt is a fast, cheap-to-iterate but less robust way to nudge and patch model behavior, working hand-in-hand with post-training; explicit emphatic wording (like all-caps NEVER) helps knock the model out of training artifacts (e.g., starting replies with 'certainly'), and once fixed in training the prompt patch can be removed.
factualpending
Speaker
Amanda AskellEvidence Quote
“I think of it as patching issues and slightly adjusting behaviors to make it better... it’s almost like the less robust but faster way of just solving problems.”
Created: 6/13/2026, 3:36:36 AM
My Notes
Loading notes...