rubrics
-
sleepcast: bedtime audio with an inverted rubric
a bedtime audio product whose generation rubric inverts every content incentive: repetition is good, drift is good, resolution is bad, and a completed play is a failure signal.
-
reward engineering for coding agents
why coding agents optimize the rubric more than the prompt.
-
reward hacking in coding agents
how poorly designed metrics produce plausible but unstable code.
-
reward rubric dsl
a small machine-readable format for scoring coding agent output.