134
LLMS Are Not Fun (orib.dev)
submitted 10 months ago by to c/programming@programming.dev
43 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 10 months ago (1 child)

Improving your input, and the system message can also be part of that. There are multiple optimizations available for these systems that people aren't really good at yet.

It's like watching Grandma google "Hi, I'd like a new shirt" back in the day and then having her complain that she's getting absolutely terrible search results.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 12 points 10 months ago* (last edited 10 months ago)

    Mmmmm. Pure "prompt engineering" feels soulless to me. And you have zero control over the endpoint, so changes on their end can break your prompt at any time.

    Messing with logprobs and raw completion syntax was fun, but the US proprietary models took that away. Even sampling is kind of restricted now, and primitive compared to what's been developed in open source.

  • permalink
  • fedilink
  • source
  • parent