I have being recently working with different agent frameworks and I couldn't agree more with the ideas in the paper.

I haven't found yet a practical use case where I would personally prefer to use an agentic pattern over a code-defined workflow, where some (managed) calls to LLMs can still happen.

I am happy to have a debate on my views on a general level beyond my personal experience and this particular situation, I didn't realize that is what was happening here.

I was taking about myself in a thread that points directly to me personally and professionally. I apologize for my over-defensiveness, it has been a long weekend.

I was doing a task that was time consuming and happened to have the expertise to improve parts of it with automation. I used this hammer myself and got the opportunity to be paid for polishing for public release.

> You go in and do what you want.

I have been in OSM way before this project.

It is true I do what I want to some extend, as any other OSM contributor, always trying to follow the existing policies in the community.

I have been manually mapping swimming pools and other features for years.

Do you think it is possible that sometimes you might perceive it that way but the thinking behind is different?

Given the different reactions, I am sure it is not you misreading it but me making a very poor choice and not including further explanation of the intended message 😅