You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/art/rewards/ruler.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -39,7 +39,7 @@ class Response(BaseModel):
39
39
40
40
41
41
DEFAULT_RUBRIC=dedent(
42
-
"""
42
+
"""
43
43
- A trajectory that achieves its goal should always get a significantly higher score than a trajectory that does not achieve its goal.
44
44
- A trajectory that achieves its goal more efficiently (eg. by avoiding unproductive detours) should get a higher score than a trajectory that achieves its goal less efficiently.
45
45
- If one trajectory is only slightly better than another, the difference in scores should be small. If it is significantly better, the difference in scores should be large.
0 commit comments