Google Search on Firefox Without AI
Google has added AI-generated summaries to its search results in the EU, prompting users to seek ways to disable the feature. A tutorial explains how to configure Firefox to use a custom Google search engine that bypasses the AI by adding a specific URL parameter. The guide also advises setting Firefox’s homepage to “Firefox Home” and optionally making the new engine the default search source.
- ▪Users have been using extensions like uBlock Origin to hide AI summaries but these do not stop the AI from running in the background.
- ▪The tutorial creates a new search engine entry in Firefox with the URL https://www.google.com/search?udm=web&q=%s to prevent AI summaries.
- ▪Firefox’s built-in or extension-provided search engines cannot be directly edited, so a separate entry must be added and optionally set as the default.
- ▪The method is designed for Firefox 153 on macOS but should work on other versions and operating systems.
- ▪tags:[
- ▪technology
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,966 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | chsxf.dev |
| Canonical URL | https://chsxf.dev/2026/07/27/18-firefox-setting-up-google-search-without-ai.html |
| Publication time | Thu, 30 Jul 2026 19:58:01 +0000 |
| Retrieval time | 2026-07-30T20:07:29.710Z |
| Last seen | 2026-07-30T20:07:29.710Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | kkQkTQUFFdod · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Google Search on Firefox Without AI 27 July 2026 Firefox Google No AI For the past few days, now that Google Search includes AI summaries in the EU, I’ve seen many people using UBlock Origin or extensions with similar capabilities to remove the AI slop at the top of the search results. However, I think this is not a good enough solution as it only cleans the output without actually disabling the feature that runs in the background. The energy will still be wasted, and the disturbance only will be put under the rug. There are better solutions for that, even if not perfect. This post will explain how to configure Firefox to use Google Search without AI. The same method should be applicable to any major browser, even though I’ve not tried it myself.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at chsxf.dev.
Discussion
0 commentsMore from chsxf.dev
