Understanding is the new bottleneck

(geoffreylitt.com)

30 points | by sebg 1 hour ago

7 comments

  • wseqyrku 1 minute ago
    If you try to spec the problem with all the painful details for the machine to undrestand, you will end up with a rust codebase.
  • alecbz 23 minutes ago
    We have LLMs try to generate descriptions of PRs for us and they're pretty universally disliked. They're always overly-complex descriptions of the mechanical changes and have no sense of motivation.

    Also, a huge reason to understand the code yourself is to make sure the LLM isn't wrong, but this doesn't work if an LLM is itself generating the understanding.

    • dylan604 1 minute ago
      Are these generated descriptions of LLM submitted changes or of human changes? If a human, shouldn't they be putting the motivation into the PR?
    • vjvjvjvjghv 19 minutes ago
      I don’t know. From my experience I get pretty good descriptions of PRs if I ask the right questions and provide some context.
    • morkalork 11 minutes ago
      I am so very tired of 2 page long PR descriptions for a 5 line change.
  • iainctduncan 28 minutes ago
    I am so dying to read more about the new/current/real bottleneck!

    Where is the bottleneck? WHERE?? Tell me! No evidence needed, just lay it on, man to man, thought-leader to thought-leader!

    • iainctduncan 24 minutes ago
      Oh wait, there it is, sitting over top of the fat part and under the cork...
  • euthymiclabs 1 hour ago
    "I read the code." -Mitchell Hashimoto

    Great code needs great understanding and agents need excellent guidance. Even in my current solo-dev work, I can't imagine making a production commit I haven't read until I understand it. I own the consequences of my code; that's a responsibility AI agents can't take.

  • hk__2 14 minutes ago
    For me the solution has been to throw away the code I don’t understand. I let the agent write the code, and if when I read it it seems unclear or needs a lot of explanation from the agent, I just throw it away and start over, or do it by myself.
  • fabiensanglard 26 minutes ago
    While the tips are good to handle the volume, I still think this sets code owner on a dangerous path.

    AI have limitation and hallucinate. Complex code will be explained in hallucinated way. At some point AI will be unable to write more because the arch has become too complex or the volume of code will be to high.

    The article I would like to read would suggest how to force LLM to architect the code like a solid tower instead of a pile of unstable mud.

    • vjvjvjvjghv 15 minutes ago
      I feel if you still architect the code and guide the LLM, it will do a pretty good job. Maybe one day the LLM will be able to do all the system architecture but that’s probably still quite some time out. I don’t even know if that’s possible considering different business needs and other factors that aren’t technical.
  • jbdamask 20 minutes ago
    pfft...I'm way past understanding
    • ch4s3 11 minutes ago
      Overstanding is the new horizon