←back to thread

My Workflow Is 70% AI, 20% Copy-Paste, 10% Panic. What's Yours?

27 points jamessmithe | 1 comments | 10 Sep 25 10:11 UTC | HN request time: 0.2s | source

Being an analyst I need to research about the market and work accordingly. With the help of ChatGPT, perplexity and Gemini, I get done 70% of my research work. The rest of the 30% is just pure brainstorming. Then if I need some graphics then I use Canva for designing them. I get the images from them. Sometimes, I create ppts too using it. If I need any videos then i usually use tool like fliki, Lunabloom Ai or invideo to generate video. These tools give me good quality AI generated videos. Then nowadays, AI is also available on social medias. It makes the job easier for me. So basically, Most of my work is completed by AI. The one thing I need to do properly is to give them proper instructions. How do you go about it?
1. ninkendo ◴[10 Sep 25 12:36 UTC] No.45196742[source]▶
I spent the entirety of yesterday, from around 8:30 until almost exactly 5pm, doing a relatively straightforward refactor to change the types of every identifier in our system, from the protobuf the database, from a generic UUID type to a distinct typesafe wrapper around UUID for each one. This is so that passing ID’s to functions expecting identifiers for one particular type vs another, is less error prone.

It was a nonstop game of my IDE’s refactoring features, a bunch of `xargs perl -pi -e 's/foo/bar/;', and repeatedly running `cargo check` and `cargo clippy --fix` until it all compiled. It was a 4000+ line change in the end (net 700 lines removed), and it took me all of that 8.5 hours to finish.

Could an AI have done it faster? Who knows. I’ve tried using Cursor with Claude on stuff like this and it tends to take a very long time, makes mistakes, and ends up digging itself further into holes until I clean up after it. With the size of the code base and the long compile times I’m not sure it would have been able to do it.

So yeah, a typical day is basically 70% coding, 20% meetings, and 10% slack communication. I use AI only to bounce ideas off of, as it seems to do a pisspoor job of maintenance work on a codebase. (I rarely get to write the sort of greenfield code that AI is normally better at.)