I believe this is why the importance of written (human) knowledge is only increasing, especially internally at companies. Written knowledge (i.e documentation) has always served as a knowledge cache and a way to transfer knowledge between people.
Without fundamental changes to the LLMs or the way we think about agentic systems, high quality, comprehensive written knowledge is the best path to helping agents "learn" over time.
^this, but many non-code documents with manual steps can also be kept up-to-date as long as there is a way (a) relate it back to the codebase or another source of truth (b) detect conflicts (when someone says something in contradiction to an existing document)
I don't really see that as a different thing. The docs and comments guide you when it comes to doing maintenance, so it's natural to use them to plan and think about the needed changes. They get updated almost as a side effect.
I guess the mindset I have internalized is that I don't really see doc writing/updating as a separate thing from coding. I do it out of habit and without really being aware of it. Or, more likely, I've just been doing this a very long time and have deeply ingrained habits.
There has been an influx of AI-generated bug reports to popular OSS projects. It's unclear if this is malicious or someone built a tool with good intention that is now causing maintainers to be inundated with issues.
Has anyone stumbled upon an AI tool that helps submit bug reports to OSS project?
We working on this at https://dosu.dev/ (open to feedback!)