fix: stop ranking for "how many parameters does GPT have" - #196
Merged
Conversation
Search results were pulling the site into weight-count queries
("how many parameters is haiku 4.5") instead of the API-settings
audience it serves. Titles, H1s and the model FAQ all matched the
count phrasing exactly.
Every page title and H1 now says "API parameters". The model FAQ no
longer asks "how many parameters does X accept", which sat in FAQPage
JSON-LD as a claim to answer count queries. Dataset JSON-LD gained
keywords and an about pointing at a DefinedTerm for the API-parameter
sense.
Adds /model-parameters-vs-api-parameters to absorb the count intent so
the 200+ model pages stop competing for it. llms.txt states the
distinction up front for AI answer engines.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Every interior page already separates page and brand with a middot. The homepage was the only one using an em dash.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
💭 Why
Google is matching the site against weight-count queries ("how many parameters is haiku 4.5", "gpt-3.5 parameters") instead of the API-settings audience it serves. The site was optimized for the wrong sense: titles, H1s and the model FAQ all matched the count phrasing exactly, while the disambiguating wording only appeared in body copy.
✨ What changed
keywordsand anaboutpointing at a DefinedTerm for the API-parameter sense./model-parameters-vs-api-parametersabsorbs the count intent, with its own FAQPage.👤 For users
Someone landing from a weight-count query gets a line under the H1 telling them it's a different number, with a link to a page that answers them honestly.
📝 Notes
The absorber page is the mechanism, not a courtesy explainer. Without one target for the count sense, Google keeps attaching it to all 242 model pages.
Track it in GSC: filter Queries by
parameters, regex-excludeapi|temperature|top_p|max_tokens|setting, and watch that share fall over 8-12 weeks.Follow-up: the concept DefinedTerm could carry
sameAsto Wikipedia/Wikidata entities for both senses. Left out until the URLs are verified.