Y
Hacker News
new
|
ask
|
show
|
jobs
Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers
10 points by
tomncooper
6 hours ago |
2 comments
dominotw
4 minutes ago
[
-
]
prompts that these evaluations were done are too trivial
chelseahermes
5 hours ago
[
-
]
[flagged]
Please enable JavaScript to continue using this application.
prompts that these evaluations were done are too trivial
[flagged]