I re-scanned 393 AI-built repos without using AI. 1 in 8 shipped a critical flaw.
This story is from 2026-10-03. It is preserved in the archive; the latest stories are on the live feed.
In September I published what a language model found across 400 AI-built repositories. The most useful criticism was also the most obvious: a model's judgement is not reproducible, and you cannot audit it. Run it again and you might get a different answer. Ask "how exactly did you count that?" and…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-03 12:14 · DEV Community — AI
I re-scanned 393 AI-built repos without using AI. 1 in 8 shipped a critical flaw.