Quoting voxium
An engineer at a large company reports Claude Code generates all specs, code, and tests, forcing 12-hour days with no human review.
Simon Willison quotes voxium, an engineer half a month into a role at a large company where all specs, code, tests, PRDs, and tickets are produced by Claude Code. The team reportedly dislikes this, with management claiming code pushes are not a bottleneck. Engineers from L1 to L7 are said to work 12-13 hour days largely prompting the model, with nobody reading the generated artifacts.
- Engineer says all specs, code, tests, and PRDs at a large company are generated by Claude Code.
- Management reportedly insists pushing code is not a bottleneck despite perceived slowness.
- Engineers from L1 to L7 work 12-13 hour days mostly prompting the model.
- Team dislikes the workflow; nobody reviews the AI-generated output.
It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. — voxium Tags: ai-misuse , llms , ai , generative-ai
This source does not provide full text. Read it at simonwillison.net.