I spent the past ~4 weeks trying out all the new and fancy AI tools for software development.
Let’s get a few things out of the way:
Learning how to use LLMs in a coding workflow is trivial. There is no learning curve. You can safely ignore them if they don’t fit your workflows at the moment.
LLMs won’t magically make you deliver production-ready code If you can’t read the code and spot issues, they’re hard to use past the PoC stage They have terrible code organization skills, making them lose themselves on even medium-size codebases. They perform better on mature, well-written, well-documented codebases. They need you to know what you want to get the best results.
By being particularly bad at anything outside of the most popular languages and frameworks, LLMs force you to pick a very mainstream stack if you want to be efficient.
Using LLMs did make me a worse software developer, as I didn’t spend as much time reading docs and thinking as before. There’s a reason why most managers suck at writing code.
Since about a year ago, “agents” have become all the rage.
What you have to understand is that an agent is simply:
Calling an LLM and giving it a list of (local) HTTP servers it can query with JSON payloads
It outputting a query instead of a normal text response
... continue reading