Obviously a lot of noise recently of maintainers trying to stop AI contributions to avoid being overwhelmed. But I'm curious if there have been any credible experiments at the opposite extreme - where repos / code can be submitted to (and reviewed) only by AI agents. I'm curious whether it's possible to have strong enough AI reviewers to manage the load and keep the project on track. Comments URL: https://news.ycombinator.com/item?id=49320927 Points: 1 # Comments: 0