Add patterns 30–34: artifacts and contamination from chat UIs#112
Open
philippdubach wants to merge 1 commit into
Open
Add patterns 30–34: artifacts and contamination from chat UIs#112philippdubach wants to merge 1 commit into
philippdubach wants to merge 1 commit into
Conversation
These five patterns appear when text is copied directly out of a chat UI without scrubbing. They do not occur in genuinely human-written text — when present, AI involvement is essentially confirmed. Sourced from Wikipedia: Signs of AI writing (revision fetched 2026-05-01), specifically the "Markup", "Citations", and "Communication intended for the user" sections. §30 Reference-markup artifacts: turn0search0, citeturn0search0, :contentReference[oaicite:0], oai_citation, [web:1], [attached_file:1], <grok_card>, utm_source=chatgpt.com, referrer=grok.com, the JSON-shaped attribution payloads. §31 Phrasal templates and placeholder text: [INSERT NAME], 2025-xx-xx access-dates, [YEAR] / [COMPANY] / [INDUSTRY], and the "forgot to fill in the blank" failure mode. §32 Markdown / wikitext contamination: leftover triple-backtick fences in prose, "Would you like me to convert this to ___?" meta-prompts the chatbot wrote to itself, lone --- breaks before every heading. §33 Section summaries / formal "Conclusion" closers: distinct from §25 (generic positive endings) — this is about the structural tic of having a "Conclusion" / "Final Thoughts" / "Key Takeaways" section at all, even when the body already made the point. §34 Didactic disclaimers: "It's important to note that...", "as always, consult a professional" — a GPT-3.5 / early-GPT-4 era tic that still leaks through on health, legal, and financial topics. README: bumps "29 patterns" → "34 patterns" and adds the new "Artifacts and Contamination" table. WARP.md: corrects the stale "25 patterns" reference to match SKILL.md's actual count. Note: there is partial overlap with open PRs blader#85 ("patterns 30-31") and blader#94 ("3 wiki-sourced patterns"). Happy to rebase or carve up if either lands first. No version bump.
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>
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 five new patterns covering the artifacts that appear when text is copied directly out of a chat UI without scrubbing. These do not occur in genuinely human-written text — when present, AI involvement is essentially confirmed.
Sourced from Wikipedia: Signs of AI writing (revision fetched 2026-05-01), specifically the "Markup", "Citations", and "Communication intended for the user" sections.
turn0search0,citeturn0search0,:contentReference[oaicite:0],oai_citation,[web:1],[attached_file:1],<grok_card>,utm_source=chatgpt.com,referrer=grok.com, JSON-shaped attribution payloads.[INSERT NAME],2025-xx-xxaccess-dates,[YEAR]/[COMPANY]/[INDUSTRY], the "forgot to fill in the blank" failure mode.---breaks before every heading.README: bumps "29 patterns" → "34 patterns" and adds a new "Artifacts and Contamination" table with the five rows.
WARP.md: corrects the stale "25 patterns" reference to match SKILL.md's actual count.
No version bump.
Overlap with open PRs
There is partial scope overlap with two open PRs — flagging in case it affects review order:
Happy to rebase, renumber, or carve up this PR if either of those lands first. If neither does, this PR can land on its own.
Test plan
Source: Wikipedia:Signs of AI writing.