8 comments

  • jaredsohn 3 hours ago

    >day or 2 max

    I've frequently seen tasks that it thinks will take weeks being done in under an hour. And it will often recommend doing X instead of Y because X requires so much extra work. Basically I just remind it that it is an LLM.

    If it worries something is error prone, I ask it to write tools to verify it.

  • vishnukool 4 hours ago

    The problem is that LLMs do not have a conceptual grounding in actual time. They estimate based on statistical correlation found in their training data which is filled with standard corporate project management timelines legacy codebases and waterfall estimates.

  • ZivenChang 2 hours ago

    they estimate based on how software is usually built in organizations, not how fast it can be built with modern AI tools and agents.

  • sieve 7 hours ago

    This is very common as they have no conception of time. They are just using ballpark figures based on what they see in the wild. I see estimates for modules in weeks/months when it can produce it in a single afternoon of prompting.

  • BeInLife an hour ago

    they estimate as if human will build it

  • dnnddidiej 6 hours ago

    You ask LLMs for estimates? Interesting.

    Probably big model providers should do calibratuons for that and add an estimation skill.

    • schappim 6 hours ago

      I've found that they declare estimates unprompted.

  • kspetkov79 7 hours ago

    They tend to turn a small change into the whole cleanup plan. Sometimes that is useful, but it makes estimates too large.