Harden long-running behavioral evaluations

This commit is contained in:
2026-09-23 00:19:35 +08:00
parent 9f54f8f5a3
commit afcd6c614e
4 changed files with 35 additions and 3 deletions
+2 -1
View File
@@ -55,7 +55,8 @@ def render_skeleton(client: JsonModel, skeleton: BehaviorSkeleton) -> str:
"are empirical observations, not explicit system laws: do not state or invent the hidden rules, "
"trigger probabilities, intermediate flags, exact query probability, or answer. Make clear that "
"all trials use one unchanged system and that the question asks which final outcome is more likely, "
"not for an exact probability. End by requiring exactly one supplied answer label."
"not for an exact probability. Present repeated histories in a compact table rather than verbose "
"paragraphs. End by requiring exactly one supplied answer label."
),
user=f"Render this intermediate representation:\n{prompt}",
schema_name="rendered_problem",