AI writes code that breaks main half as often
On the benchmark cohort, a green PR breaks main about 0.77% of the time at 2 to 5 engineers (1 in 130), but 12.5% of the time once a repository passes 40 engineers (1 in 8). On private codebases overall the rate is 5.1%; on open source it is 1.1%."}},{"@type":"Question","name":"Does AI-assisted code break main more often?","acceptedAnswer":{"@type":"Answer","text":"No. In the data, AI-assisted PRs broke main about half as often as non-AI PRs (1.9% versus 4.4%).
- ▪On the benchmark cohort, a green PR breaks main about 0.77% of the time at 2 to 5 engineers (1 in 130), but 12.5% of the time once a repository passes 40 engineers (1 in 8).
- ▪On private codebases overall the rate is 5.1%; on open source it is 1.1%."}},{"@type":"Question","name":"Does AI-assisted code break main more often?","acceptedAnswer":{"@type":"Answer","text":"No.
- ▪In the data, AI-assisted PRs broke main about half as often as non-AI PRs (1.9% versus 4.4%).
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,762 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 | Mergify |
| Canonical URL | https://mergify.com/reports/state-of-merge-queues-2026 |
| Publication time | Tue, 28 Jul 2026 08:52:42 +0000 |
| Retrieval time | 2026-07-28T08:59:19.831Z |
| Last seen | 2026-07-28T08:59:19.831Z |
| 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 | r4w52yamOMfS · 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
{"@context":"https://schema.org","@type":"Article","headline":"State of Merge Queues 2026","description":"What 200,000 merges across 477 engineering teams reveal about the gap between approved and merged: the broken-main rate scales 16x with team size, private code breaks main 4.5x more than open source, and AI-assisted PRs break main half as often.","image":"https://mergify.com/og/reports/state-of-merge-queues-2026.png","datePublished":"2026-07-27","dateModified":"2026-07-27","author":{"@type":"Person","name":"Julien Danjou","jobTitle":"Co-founder & CEO of…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Mergify.
Discussion
0 commentsMore from Mergify
