docs: add self_audit direction notes to module docstring#591
Merged
Conversation
Captures thoughts on future improvements to the self_audit checklist:
- A dedicated system prompt for VIOLATES_KNOWN_PHYSICS to reduce
false positives (elephant-alpha model especially prone to flagging
non-physics plans as physics violations).
- Proposed new checklist items:
* Find fabricated evidence (hallucinated laws, articles, citations).
* Call out fake confidence where evidence is insufficient.
* Attack on vague filler language ("develop a robust strategy",
"implement a communication strategy") that doesn't specify the
actual strategy.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds notes to the top-of-module docstring in
self_audit.pycapturing directions worth exploring:elephant-alphain particular flags non-physics plans as physics violations ("faster than light travel" on documents unrelated to FTL), while doing fine on other checklist items. A separate tailored prompt might reduce false positives without disturbing the rest of the audit.Why commit these as a docstring
Keeps future-direction notes co-located with the code they affect, so anyone touching
self_audit.pysees them immediately. These are deliberately notes, not implementation — related PR #585 covers the ongoing work on the physics false-positive.🤖 Generated with Claude Code