kbin_space_program

  • 0 Posts
  • 56 Comments
Joined 9 months ago
cake
Cake day: February 23rd, 2024

help-circle





  • You can make it more deterministic by reducing the acceptable range of answers, absolutely. But then you also limit your output, so thats never really a good use case.

    Randomness is a core functionality of not just LLMs, but the entire stack that has resulted in LLMs. Yes you can get a decently consistent answer, but not a deterministic one. Put another way, with LLMs being at max constraint, you can ask them to add 1+1. You’ll usually get 2. But not nearly always.









  • Best project Ive worked on, we went and implemented a scrict code standard, based on the code standard that a firm that contracted my team to do the work had.

    Worked perfectly. Beautiful, maintainable code. Still used today without major reworks, doesnt need it. Front end got several major updates, but the back end uses what is now called microservice architecture, and we implemented it long before the phrase was common.

    Got the opportunity to go back to it this year. Devs with the 2nd firm not only ignored all of the documentation we put out, they ignored their own coding standards document.