How much can you delegate to agents?

(newsletter.posthog.com)

48 points | by duck 11 hours ago

9 comments

  • parasti 29 minutes ago
    This post is full of things opposite of what I've found. An agent (claude code at least) will certainly refactor feature flags better than I ever could and is less likely to miss special cases. What the agent struggles with is business knowledge - context I hold in my head as a human communicating with other humans and working on a codebase over a long period of time.
  • jolaflow 7 hours ago
    Interesting. When it comes to auditing, I think there is also another layer to be verified - the intent. We have tooling for static analysis and automated tests, but drift in intent or vision is hard to detect.

    After leaving agents unsupervised for longer periods of time, the biggest questions tend to be "how did it arrive at this conclusion?" and "did we drift from the initial vision?". Typically these questions are hard to answer as you only review the final state of the workflow.

    I recently built an issue tracker that does offer time-traveling as a core feature. Somewhat unexpectedly this turned out to provide a much sought for overview allowing for a better workflow audit, as detailed here: https://dev.to/ljtn/vision-drift-addressing-the-next-problem...

    Would be interested to hear your thoughts. I guess vision drift would classify as something that is hard to reverse, because you often don't realize it has happened until much later.

  • SOLAR_FIELDS 2 hours ago
    This is a very long form way of saying “understand the work you are dispatching, and if you don’t, ask questions until you do”
    • Frieren 2 hours ago
      > “understand the work you are dispatching, and if you don’t, ask questions until you do”

      My rant about this, not directed to the commenter but in general:

      I wish people would have been so interested on discussing and planning with teammates like they seem with AI tools.

      Because this is nothing new. Communication, knowing what you are doing, planning... was already a mandatory step for any engineering task.

      And if people that use planning with AI then ignore their teammates, other teams, etc. then it is time to reconsidering their way of working.

      • SOLAR_FIELDS 2 hours ago
        Dealing with humans is way harder than dealing with a machine that is programmed to agree with you
        • sixtyj 1 hour ago
          Yes, shouting at clouds is easier with LLM :) But those clouds are deaf, sometimes.
  • ChicagoDave 7 hours ago
    I work on my MacBook in direct terminal sessions or in a container with no safeguards.

    I save the container for well-planned units of work that can easily be repeated and validated on a branch.

    I use direct sessions when I expect and the plan dictates that Claude might go off target and I need to hold the steering wheel.

    Fable has increased my use of the container option.

  • ChulioZ 6 hours ago
    How do you draw the line between a human review at level 1 and a human safety gate at level 2?
  • apical_dendrite 7 hours ago
    There are so many other factors. Will people be pissed if they expected your output and got AI slop instead? Will you lose context on something that you really need to understand?
  • bhkdotdev 7 hours ago
    [dead]
  • drybka 9 hours ago
    [flagged]