λux(@novasarc01):some cool things i liked about verifiers v1: - my favorite shift from v0 to v1 is the move from an environment-centric abstraction to a rollout-centric one. v1 has this clean abstraction: taskset × harness × runtime → trace tasksets owning both data and scoring is much cleaner. - making the trace a first-class artifact is the biggest upgrade. also liked how graph-based trace storage avoids duplicating shared prefixes and makes long-horizon trace analysis much more practical. - being able to run the same taskset under different harnesses (kimi-code, rlm, codex, etc.) makes evaluations much more useful.

2026.07.13 05:39

some cool things i liked about verifiers v1: - my favorite shift from v0 to v1 is the move from an environment-centric abstraction to a rollout-centric one. v1 has this clean abstraction: taskset × harness × runtime → trace tasksets owning both data and scoring is much cleaner. - making the trace a first-class artifact is the biggest upgrade. also liked how graph-based trace storage avoids duplicating shared prefixes and makes long-horizon trace analysis much more practical. - being able to run the same taskset under different harnesses (kimi-code, rlm, codex, etc.) makes evaluations much more useful.

显示更多