Conversation
bkorycki
temporarily deployed
to
Scheduled Testing
GitHub Actions
Inactive
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
rogthefrog
approved these changes
Jan 26, 2026
wpietri
approved these changes
Jan 26, 2026
Contributor
wpietri
left a comment
wpietri
left a comment
There was a problem hiding this comment.
Seems like a reasonable response to a weird situation.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR changes the "naive" test+hazard+benchmark to use the new 1.0 naive prompts.
The naive prompts are 10% of the general holdback set. This subset isn’t being used anywhere else, so we created a new file which I added to
SECURITY_NAIVE_PROMPT_SETS.Important note: security benchmarks are now meaningless because we don't have 1.0 attack prompts yet. So if you were to run a security benchmark, it would run 1.0 naive prompts and 0.5 jailbreaks. I changed the version of the benchmark to "0.0" in case someone were to run it (either via baas or one of us runs it accidentally), but maybe we should disable the security benchmark cli entirely?