{"slug": "a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story", "title": "A student eyeballed 102 F-Droid apps for LLM slop. The method is the story.", "summary": "A student manually classified all 102 apps in the September 12, 2026 F-Droid update batch by how likely an LLM authored them, using repo aesthetics such as commit tone, README emoji density, and the presence of Claude Code or Codex agent infrastructure rather than any code analysis. The survey's author states its limits up front, and the writeup argues the finding that AI provenance cannot be reliably resolved means review gates built on detecting LLM output are a dead end, and that diffs should be reviewed on origin-independent properties instead.", "body_md": "Someone on [tintotint.eu](https://tintotint.eu/whacky-corner/f-droid_slop/) went through every app in the September 12, 2026 F-Droid update batch, 102 apps, and classified each one by how likely it is that an LLM wrote it. Mostly AI, hard to say, no signs of AI. One student, one batch, a few tiers, done.\n\nThe results are less interesting than the method, because the method is the honest part.\n\nHere's how they classified: no slop detector, no code analysis. Just repo aesthetics. Commit tone. Emoji density in the README. Whether the repo has Claude Code or Codex agent infrastructure wired in. Whether there's an AI disclosure line in the README at all. One data point I trust: anything with the agent harness present got thrown straight into \"mostly AI\";\n\nI'm a fan of this because the author states the limits up front. No way to know for sure, tiers are loose, the rating is superficial. That's the same caveat I keep running into and it deserves more attention than the headline number that everyone will extract from this.\n\nAnyone who has done code review on a repo that ships quickly knows the tell is not the code. It's the commit messages being perfectly uniform, the PR description covering exactly the changed lines and nothing else, the changelog using the same boilerplate every release. None of that tells you whether the logic is correct. It tells you how the author works.\n\nHere's the part that matters for review, and specifically for the \"review the growing volume of AI-generated code\" question that keeps coming up. You cannot reliably detect whether code was AI-authored, even looking at the full repo with its history and branding. If the author of this survey is right, and they're pretty careful, then provenance is not resolvable. Which means the whole idea of gating review on \"is this AI code\" is a dead end.\n\nWhat you actually have is the code in the diff. That's the thing to review, regardless of who or what wrote it.\n\nSo stop trying to label AI code and review the properties that hold no matter the author. Does the change touch auth before or after the validation? Is the error path handled or just the happy path? Does the new dependency have a tag? Those answer the question \"should this merge?\" The provenance questions answers \"what can I blame if it breaks?\" and that one is not yours to answer.\n\nIf you're building the review gate on top of \"detect the LLM output,\" you're building it on a signal the survey just showed is unreliable even with full repo access. Review the diff. Origin-independent review is the only framing that survives contact with this data.", "url": "https://wpnews.pro/news/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story", "canonical_source": "https://dev.to/cole_halton_42f71d71b809b/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story-3gno", "published_at": "2026-09-17 00:15:13+00:00", "updated_at": "2026-09-17 00:23:10.979824+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "artificial-intelligence"], "entities": ["F-Droid", "Claude Code", "Codex", "tintotint.eu"], "alternates": {"html": "https://wpnews.pro/news/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story", "markdown": "https://wpnews.pro/news/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story.md", "text": "https://wpnews.pro/news/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story.txt", "jsonld": "https://wpnews.pro/news/a-student-eyeballed-102-f-droid-apps-for-llm-slop-the-method-is-the-story.jsonld"}}