2 comments

  • ikidd 2 hours ago

    I remember the idea of "swear at the LLM to get better results" and I even think it somewhat worked, at least for a while.

    This is probably how we'll end up with a HAL9000 burning the world to the ground.

  • polotics 8 hours ago

    Pretty please ask Claude to start with benchmarks that measure your approach against other approaches. I did read all and only found:

    Selected numbers from live system runs:

    Scenario , Naive shell approach , Hollow API , Savings

    Code search , 21636 tokens , 987 tokens , 95%

    Agent drift (cons. rate) , 35% (cold start) , 70% (with handoff) , 2x

    That is a lot less than enough to justify a git clone.