Harden long-running behavioral evaluations
This commit is contained in:
@@ -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",
|
||||
|
||||
Reference in New Issue
Block a user