Era-aware AI vocabulary breakdown + speculative gap-filling pattern#111
Closed
philippdubach wants to merge 1 commit into
Closed
Era-aware AI vocabulary breakdown + speculative gap-filling pattern#111philippdubach wants to merge 1 commit into
philippdubach wants to merge 1 commit into
Conversation
…tern Two changes sourced from Wikipedia: Signs of AI writing (revision fetched 2026-05-01). §7 (AI Vocabulary): replace the flat high-frequency word list with the era-specific clusters now documented on the wiki page (GPT-4 / GPT-4o / GPT-5 eras). Add 'bolstered' and 'meticulous/meticulously' to the master list, and a one-line caveat about literal vs figurative usage. §21 (renamed to "Knowledge-Cutoff Disclaimers and Speculative Gap-Filling"): cover the newer retrieval-augmented pattern where the model, having failed to find a source, writes a paragraph about not having found one and then speculates that the subject "maintains a low profile" or "keeps personal details private." Adds a second before/after example for the gap-filling case. README: tighten the §21 row label to reflect both subpatterns. No version bump (leaving that to the maintainer to coordinate with the open v2.6.0 PRs). No new patterns; pattern count stays at 29.
4 tasks
philippdubach
added a commit
to philippdubach/humanizer
that referenced
this pull request
May 1, 2026
Brings the fork's main branch in line with the maintained local v2.6.0, consolidating the changes that are also opened as focused PRs against blader/humanizer (blader#111, blader#112, blader#113): - §7 expanded with era-specific AI vocabulary clusters (GPT-4 / GPT-4o / GPT-5 eras), plus 'bolstered' and 'meticulous' added to the master list and a literal-vs-figurative caveat. - §21 renamed to "Knowledge-Cutoff Disclaimers and Speculative Gap-Filling"; covers the retrieval-augmented "maintains a low profile" / "keeps personal details private" speculation pattern. - New patterns §30-34: reference-markup artifacts (turn0search0, oaicite, utm_source=chatgpt.com, etc.), placeholder leftovers, Markdown/wikitext contamination, formal "Conclusion" closers, didactic disclaimers. - New Detection Guidance group: what NOT to flag (false positives), signs of human writing to preserve, and per-model LLM idiolects. Frontmatter version bumped to 2.6.0. README pattern table updated (29 → 34 patterns) with a new Artifacts and Contamination section and a pointer to Detection Guidance. WARP.md count corrected from the stale "25 patterns" to 34. Sourced from Wikipedia: Signs of AI writing (revision fetched 2026-05-01).
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>
blader
added a commit
that referenced
this pull request
May 27, 2026
- §14: turn em-dash "overuse" into a hard cut (no em or en dashes in the final rewrite), with a replacement ladder and a final scan. Idea from #96. - §21: expand to cover speculative gap-filling ("maintains a low profile," "keeps personal details private") where a model invents filler instead of saying a source is missing. Idea from #111. - New pattern #30, diff-anchored writing: describe the thing as it is, not as a narration of what changed. Idea from #81. Hand-ported lean versions rather than merging the source PRs. 30 patterns total; README and AGENTS.md updated to match. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Owner
|
Adopted the speculative gap-filling half in v2.7.0 — §21 now covers 'maintains a low profile / keeps personal details private' as unsourced filler. Left out the era-vocabulary taxonomy on purpose (it's forensic dating that ages quickly; we just removed a similar model-fingerprinting section). Thanks for surfacing the gap-filling tell. |
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
2 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.
Summary
Two narrowly scoped updates sourced from the current revision of Wikipedia: Signs of AI writing (revision fetched 2026-05-01).
bolsteredandmeticulous/meticulouslyto the master list, plus a one-line caveat about literal vs figurative usage (e.g., underscore as a literal underline, delve in geology).No new patterns; pattern count stays at 29. No version bump — happy to defer that to whatever coordination you do with the open v2.6.0 PRs (#85, #98).
Test plan
Source: Wikipedia:Signs of AI writing — see "High density of AI vocabulary words" and "Knowledge-cutoff disclaimers and speculation about gaps in sources" sections.