Uh oh!
There was an error while loading. Please reload this page.
Replace negative-priming with positive framing and reduce output verbosity in identify step - #473
Closed
neoneye wants to merge 1 commit into
Closed
Replace negative-priming with positive framing and reduce output verbosity in identify step#473neoneye wants to merge 1 commit into
neoneye wants to merge 1 commit into
Conversation
…osity
Replace "Do NOT include 'Controls ... vs.', 'Weakness:'" with positive
framing ("Focus on cause-effect relationships and factual outcomes").
Reduce output targets: consequences 2-4 → 2-3 sentences, options
"a full sentence" → "one sentence", review_lever trimmed to "1-2
sentences" without "See system prompt section 4 for examples". Helps
gpt-oss-20b (reasoning model) complete within 600s plan budget — the
identify step makes 3 LLM calls per plan, and slow providers can take
200-1000s per call.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>neoneye
commented
Mar 31, 2026
MemberAuthor
Self-improve iteration — analysis 70Verdict: CONDITIONAL
Closing — will fix system prompt consistency and strengthen number-evidence constraint in next PR. |
neoneye added a commit
that referenced
this pull request
Mar 31, 2026
…e constraint
Replace negative prohibition ("Do NOT include 'Controls ... vs.'") with
positive framing. Align all three length targets (field desc ×2, system
prompt) to "2-3 sentences" — PR #473 only updated field descriptions,
leaving system prompt at "2-4" which haiku followed instead.
Strengthen number-evidence constraint: "Never invent percentages, costs,
or timeframes — only cite numbers that appear in the project context."
Placed before the cause-effect directive to prevent models from
fabricating specifics to satisfy cause-effect framing.
Reduce options to "one sentence" and review_lever to "1-2 sentences"
for conciseness, helping gpt-oss-20b stay within 600s plan budget.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This was referenced Mar 31, 2026
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 freeto 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
"Do NOT include 'Controls ... vs.', 'Weakness:'"with"Focus on cause-effect relationships and factual outcomes"in consequences field (bothLeverandLeverCleaned)Supersedes #471 (same positive framing fix, but #471 lacked the output reduction needed for gpt-oss-20b).
Test plan
🤖 Generated with Claude Code