Show HN: LLM Based Spark Profiler

(datasre.ai)

27 points | by ambrood 9 days ago ago

6 comments

  • vector_spaces 9 days ago ago

    Maybe you mentioned it in your demo and I missed it, but how does this differ pasting the log messages to ChatGPT / Claude / another LLM? Is it mainly that yours can iterate over a large logfile without blowing up the context window?

    Does it suffer from the same issue as other LLMs, where it will always identify potential optimizations or improvements even if none are truly needed?

    • ambrood 9 days ago ago

      > Maybe you mentioned it in your demo and I missed it, but how does this differ pasting the log messages to ChatGPT / Claude / another LLM? Is it mainly that yours can iterate over a large logfile without blowing up the context window?

      We do quite a bit of aggregation over the log file, and generate summary stats and choose what bits to stuff in the LLM. Plan to support more platforms than just spark.

      > Does it suffer from the same issue as other LLMs, where it will always identify potential optimizations or improvements even if none are truly needed?

      Funnily enough, instructing sonnet-3.7 to not suggest unnecessary optimisations seems to have done the trick!

  • emgeee 9 days ago ago

    fellow co-founder here! One fun thing about this project is the entire frontend was vibe-coded using Bolt in a few days.

    • skeptrune 9 days ago ago

      Very awesome. Not having to burn time on a UI that looks and feels nice is a huge win.

  • ztratar 9 days ago ago

    Also curious how the agent works?

  • curtisszmania 9 days ago ago

    [dead]