Quoting Kenton Varda

Simon Willison's Blog News
ai generative-ai llms ai-assisted-programming code-review change-descriptions moratorium

Summary

Kenton Varda announces a moratorium on AI-written change descriptions (PR/commit messages, issues/tickets) on his team, citing that AI omits high-level framing needed for code review and produces worse-than-useless descriptions.

No content available
Original Article
View Cached Full Text

Cached at: 07/09/26, 07:56 AM

# A quote from Kenton Varda Source: [https://simonwillison.net/2026/Jul/8/kenton-varda/](https://simonwillison.net/2026/Jul/8/kenton-varda/) 8th July 2026 > I just declared a moratorium against AI\-written change descriptions \(e\.g\. PR and commit messages, also issues/tickets\) from my team\. AI was writing change descriptions that were worse than useless to me as I tried to review PRs: outlining details of the code that could easily be seen by looking at the code, but omitting the higher\-level framing needed to understand broadly what the code is doing\. —[Kenton Varda](https://twitter.com/kentonvarda/status/2074924213983740233) Posted[8th July 2026](https://simonwillison.net/2026/Jul/8/)at 8:03 pm ## Recent articles - [sqlite\-utils 4\.0, now with database schema migrations](https://simonwillison.net/2026/Jul/7/sqlite-utils-4/)\- 7th July 2026 - [sqlite\-utils 4\.0rc2, mostly written by Claude Fable \(for about $149\.25\)](https://simonwillison.net/2026/Jul/5/sqlite-utils-fable/)\- 5th July 2026 - [Have your agent record video demos of its work with shot\-scraper video](https://simonwillison.net/2026/Jun/30/shot-scraper-video/)\- 30th June 2026 This is a**quotation**collected by Simon Willison, posted on[8th July 2026](https://simonwillison.net/2026/Jul/8/)\. [ai2,107](https://simonwillison.net/tags/ai/)[generative\-ai1,864](https://simonwillison.net/tags/generative-ai/)[llms1,831](https://simonwillison.net/tags/llms/)[ai\-assisted\-programming394](https://simonwillison.net/tags/ai-assisted-programming/)[kenton\-varda5](https://simonwillison.net/tags/kenton-varda/)

Similar Articles

Quoting Armin Ronacher

Simon Willison's Blog

Armin Ronacher criticizes AI-generated bug reports for being verbose, inaccurate, and overconfident, and advocates for structured human-written issue reports.

When I reject AI code even if it works

Hacker News Top

The author explains why they often reject AI-generated code even when it works, citing reasons like inability to explain the approach, overly large diffs, premature abstractions, and reduced system reasoning, and argues for mandatory human review.

Reducing the cognitive load of AI changes

Lobsters Hottest

Andrew Moffat shares a pre-review workflow for AI-generated code: use a prompt to extract bespoke LLM-chosen terminology, let the human confirm or override each term, then have the AI do a global find-and-replace so the code reads like it came from the reviewer's own brain, reducing accumulated cognitive load.

Write for people

Lobsters Hottest

Vicki Boykis argues that AI-generated jargon and verbose explanations are making codebases harder for humans to navigate, and advocates for clearer, more concise writing.