| ▲ | renato_shira an hour ago | |
the real issue here isn't that an AI wrote a PR, it's that someone configured an agent to operate without any human review loop on a public repo. i use AI agents for my own codebase and they're incredibly useful, but the moment you point them at something public facing, you need a human checkpoint. it's the same principle as CI/CD: automation is great, but you don't auto deploy to prod without a review step. the "write a blog post shaming the maintainer" part is what really gets me though. that's not an AI problem, that's a product design problem. someone thought public shaming was a valid automated response to a closed PR. | ||
| ▲ | chrisjj an hour ago | parent [-] | |
> someone configured an agent to operate without any human review loop Risky assumption, there. | ||