docs: cut marketing filler from user-facing prose - #11325
Open
localai-bot wants to merge 1 commit into
Open
Conversation
A no-ai-slop detect pass over all 85 docs pages and the 8 website content files. The docs came out clean on every pattern that actually got the blog post criticized on HN: zero faux-insight setups, zero unearned framing, zero ledger metaphors, zero pre-chewed numbers, zero importance puffery, zero weasel attribution, zero recap endings, zero rhetorical setups. What was left was vocabulary, so that is all this changes. Ten edits in eight files, no links or code blocks touched: - overview.md: "In today's AI landscape, privacy, control, and flexibility are paramount" and "Ready to dive in?" - architecture.md: "seamlessly integrate ... effortlessly implemented" - customize-model.md: "is utilized", "utilizes a shorthand format" - advanced/_index: "fully leverage LocalAI's capabilities beyond basic usage" - agents.md, object-detection.md, text-to-audio.md, faq.md: leverage/seamless used as filler. text-to-audio also had "before the api provide its response". Deliberately left alone: "GPU utilization", "KV utilization" and "highest-leverage knob" are the correct technical terms, not filler. The docs are reference material and read like it. They do not need the treatment the blog posts got. Co-Authored-By: Claude Opus 5 (1M context) <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #11324. The question was whether the docs need the same treatment. Mostly no, and here is the evidence.
What the detect pass found
A mechanical scan of all 85 docs pages plus the 8 website content files (117k words) against the
no-ai-sloppattern set:the honest reading,the real question)what X buys,paid for in)Every pattern that got the engines post quoted back at us on HN scored zero across the entire documentation tree. That is the expected result: reference documentation is supposed to be flat, repetitive and personality-free. The blog's problem was a borrowed personality, and the docs do not have one to remove.
README.mdscored zero on everything.What this PR changes
Only the vocabulary, which was the one category with real hits. Ten edits in eight files. No links, no code blocks, no commands touched (verified per-file).
The concentration was
docs/content/overview.md, the docs landing page and the most marketing-adjacent page in the tree:Also
seamlessly integrate ... effortlessly implemented as a substitutein architecture.md, twoutilized/utilizesin customize-model.md, and four filler uses of leverage/seamless.text-to-audio.mdalso had a grammar bug in the same sentence (before the api provide its response).Deliberately not changed
GPU utilization,KV utilization,highest-leverage knobare the correct technical terms, not filler.retained for at most 90 s — a turn that genuinely never pauses). The skill's own rule says not to flag an em dash on its own; plenty of people have typed them by hotkey for decades.reference/_index.en.mdandadvanced/_index.en.mdthese are a consistent icon-per-topic navigation convention, not decoration sprinkled through prose. That is a design decision, not a writing one..agents/,CLAUDE.md, MCP prompt files. These score high but are agent-facing instructions, not prose anyone reads as writing.Recommendation
Do not rewrite the docs. Keep the
no-ai-sloppass for the blog and the landing page, where there is a voice to get wrong.