‹ BackHN Continuity

Thread

The Four Horsemen of Agentic Coding

114 points · 89 comments · haute_cuisine

  1. JV00 · · focus · HN ↗
    Disagree on the slop point. By now the code of frontier models works well, and the need to read it is gone. The Claude word salad problem was pretty much solved with the 5.5 opus release.

    The other 3 points made in article make sense though.

    1. tschellenbach · · focus · HN ↗
      I don't know why people are downvoting this. It depends on what you're building.

      AI build me a cost overview of xyz: works perfectly without ever looking at the code

      AI build me unreal engine 5 level graphics, or a database, or infra at high scale: this will need some active steering for now :)

      1. JV00 · · focus · HN ↗
        And even for active steering, does it require reading the code? Iteration can be done on the result of the work itself, abstracting code away
      2. smashed · · focus · HN ↗
        They will do these prompt just fine but the result will be a near identical copy of an open source version. And it won't tell you it cloned some existing engine, because it does not know, it just pulled it out from its model. Now you have an AI slopped 3d engine or DBMS no-one cares about that will just rot.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.