Add supervised analysis tools #42
Draft
Conversation
This file contains 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 join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
These are helpers to debug and figure out why tasks are easy/hard. Currently inspired by the results from https://www.anthropic.com/research/probes-catch-sleeper-agents, but I'll probably add a few other tools as well. Making an extra
analysispackage for this to make clear that these are not valid detectors (since they use labels); should probably move theSupervisedProbethere as well.Currently a lot of duplicated code, I think we might want to use something inspired by TorchMetrics as a general interface for tracking statistics for a stream of data, and share that between detectors and tools as much as possible.