[edanm]

One thing I'd love to know - how do you balance time spent "building" vs. time spent "researching"?

The writing, I understand - you do it relatively quickly because of a lot of practice. But I feel like just reading up on the AI news every week takes up a significant amount of time - time that can't be spent researching/building things.

I'm wondering how you balance that.

[simonw]

Having relevant projects is key. My https://llm.datasette.io projects gives me the ideal playground for trying stuff out - any time a new API model comes out I can spin up a new plugin to for LLM, which is a great way to try the model with limited development time (most API plugins are a few dozen lines of code).

I've managed to balance building vs writing a lot better in the past - I lost that balance in November and December, I'm trying to get it back for January.

[edanm]

Oh that's cool. We've been blogging about AI eng recently, but the project is often "try this idea/tool/library in order to write a blog post about it".

Having some kind of standard "I need to integrate this new thing with an existing codebase" makes a great standard project.