Add patterns 30-31, expand rules 9 and 14 (v2.6.0)#85
Open
shoal-rat wants to merge 1 commit into
Open
Conversation
5 tasks
3 tasks
This was referenced May 1, 2026
duathron
added a commit
to duathron/humanizer-ext
that referenced
this pull request
May 22, 2026
- Add DETECTION GUIDANCE section (false positives, human-writing signs, LLM idiolects) so editors know what NOT to flag (PR blader#113) - Add Tier-1 AI-iness density pre-flight in Full mode; auto-drops to Quick when density = 0 to protect human-first drafts (PR blader#115 adapted) - Expand blader#7 with era-specific vocabulary clusters (GPT-4 / GPT-4o / GPT-5 eras) and figurative-vs-literal caveat (PR blader#111) - Expand blader#9 with "rather than" dismissals + on-the-table test (PR blader#85) - Expand blader#14 with paired em dash bracketing + 4 fix options (PR blader#85) - Expand blader#21 with speculative gap-filling ("maintains a low profile" template detection) (PR blader#111) - Expand blader#23 with three more didactic disclaimers (subsumes pattern 34 from PR blader#112) - Expand blader#25 with structural "## Conclusion" section note - Add pattern blader#35 Debunking-Pose Headings -- heading-level AI tells that slip through prose-only passes (PR blader#116) - Add patterns blader#36 Conditional Frame Stacking and blader#37 Miscalibrated Epistemic Confidence (PR blader#85) - Add patterns blader#38 Reference-Markup Artifacts, blader#39 Phrasal Templates / Placeholder Text, and blader#40 Markdown / Wikitext Contamination -- three chat-UI copy-paste tells that confirm AI involvement (PR blader#112) - Extend domain overrides for blader#35-37; blader#38-40 are universal - Extend final AI audit from 9 to 13 points - README: pattern count 34 -> 40, three new section rows, updated fork-differentiator table, 3.2.0 version-history entry Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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.
What this adds
Four improvements derived from real editing work on academic prose:
Expanded Rule 9 — "rather than" overuse
The existing rule covered "Not only…but" and tailing negations. Added "rather than" as a third form of the same pattern — AI stages a contrast by dismissing an alternative (Y) that nobody was claiming. Added a test: ask whether the discarded alternative is actually on the table. If not, just say X.
Expanded Rule 14 — paired em dash bracketing
The existing rule covered general em dash overuse. Added the specific case of paired bracketing (X — elaboration — continues), which looks inserted rather than written. Includes four fix strategies keyed to the type of insertion (list, appositive, parenthetical, subject expansion) and an exception for short, earned, non-repeated brackets.
New Rule 30 — Conditional frame stacking ("If X…" clusters)
AI hedges its own conclusions with multiple "if the argument holds… if the reading is right…" clauses in the same passage. One conditional at a genuine branching point is fine. A cluster of them in a conclusion signals the writer isn't standing behind their own work. Fix: state what the argument found; reserve "if" for real analytical branches.
New Rule 31 — Miscalibrated epistemic confidence
A two-sided rule. AI swings between over-asserting (loading claims with "decisively," "fundamentally," "completely") and over-hedging ("appears to have arguably," "may have somewhat"). Both are tells. The fix is never to replace one extreme with the other — it is to narrow the claim to what the evidence actually supports. Includes a "critical rule": don't fix over-assertion by adding hedges.
Version
2.5.1 → 2.6.0
Pattern count
29 → 31