Ask HN: How do you guys stay on top of the code that is generated?
I have been working on a new service from scratch and AI has spat out 1000s of LOC and while I leveraged on it quite a bit for the design of the service, I need to know exactly what is happening in every single line of code. This has increasingly become a problem for me, especially when working on something new from scratch, is there any plugin, skill, prompt that makes it easier to understand a codebase in-depth?
7 comments
[ 0.25 ms ] story [ 22.8 ms ] threadLately though, I've switched tact a bit and have resurrected some ~20yr old research called Behaviour Tree Engineering or Behaviour Trees, so I'm now writing specifications called BT specs.
e.g: https://bte.mills.io/s/v4Mjbyf0OBJWm5YRLwG5XiIH
For tools and architecture,I design data structures and let the LLM write the code, in small steps. Lots of discussion with the LLM. What Cory Doctorow calls centaur mode - a human mind augmented with a more powerful body. Applies to side projects and $DAYJOB.
For applications, I rewrote a framework of mine that I used 2003-2009. It is highly constrained so the LLM has few options to improvise. I can just tell it what features to add and it adds them without much in the way of slop. I still find code repetition which I just tell it to clean up.
Other than that, on other projects that I fully vibecoded, it's just impossible to keep with the codebase. Just blind trust the AI models on that, and never do it on a serious production product.