Repple (she/her)

  • 0 posts
  • 6 comments
Joined 3 years ago
Cake day: June 11th, 2023
  • Every time I test and LLM solution and am pleased with how well it works, and I look at the code and it looks reasonable, it’s a lie. It may work, and even look okay, but unless the change was minuscule it’s always doing weird things when I look closely. By the time I’m done fixing the code I could have done it significantly faster myself.

    Edit: in case anyone is wondering I only ever use frontier models (the anthropic and openAI ones), I have unlimited access to them from work and mandates to use them.

  • I grew up with it and as I age I identify with those generations more and more. When I was young I didn’t want to deal with people to get things done, and to a certain extent I still feel that way, but we’ve given up so much for those touches of convenience and so many times we made the simplest use cases easy while completely fucking over the less common ones.

    For example, a couple times within the last few years I’ve needed to check into hotels early in the morning. This has traditionally been easy: book starting the night before, call the front desk, let them know and they make sure not to give the room away. Well, seems like now some hotel chains only direct calls to the call center and don’t have a pathway to reach the front desk anymore. I tried telling them and they said they let the front desk know, and both times the room was cancelled.

    Big corporations have too much power and it’s too hard to avoid using them. I’m lucky enough to have enough money where I can afford to go out of my way to choose small businesses but most people are really limited in how much they can do this.