‹ BackHN Continuity

Thread

The problem is not AI code, but not knowing about system architecture or intent

388 points · 240 comments · zazuke

  1. andy_ppp · · focus · HN ↗
    I don't really understand all the negativity - I've delivered amazing robust solutions at about 10x my previous rate I think and can make dramatic cross code changes on awful legacy code bases with ease. I just added some complex prev/next navigation across a load of detail pages pages that rely on the current search, a new PDF generation system that uses a queue and workers and absolutely tones of changes to a legacy ERP system that would be unworkable without AI.

    Dealing with legacy messes I used to get frustrated and bored of making the improvements, now it's easy to clean up code bases and write loads of tests. I asked Astra to come up with a plan for Playwright testing the whole App, I have not built it yet but the flows suggested were fantastic as was the ephemeral database we plan to create for CI.

    I built my friends portfolio website almost entirely vibe coded in 4 hours and it looks unbelievable, we added so much slickness (he's a designer) just prompting together. I used a CMS I had never used once before and it was so so easy to do without any of the usual need to read docs about everything.

    I've done so much devops now I'm actually fairly confident that me and an AI can do anything you want in terms of deployment/infra and scaling from AWS to Terraform to whatever.

    Anyway my main concern about this technology is not that it is crap at coding it's that the improvements in how it codes and thinks are absolutely dramatic which is extremely scary - it has come so far in a year I wonder what the next year will bring.

    1. jasondigitized · · focus · HN ↗
      I'm with you here. If we skate to the puck, LLMs will continue to write tighter and tighter code, comments, unit tests, integration tests, etc. I would also assume that it will become increasingly good at code organization, architecture, and understanding intent. i feel like I am a series of monthly shifting of the goal posts...."LLMs can't autocomplete code", "LLMs can't write a high quality function", "LLM's can't understand small repos". "LLM's can't understand legacy code bases".....
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.