111
Reese Witherspoon Doubles Down on Telling Women to Learn AI: Jobs We Hold Are ‘Three Times More Likely to Be Automated By AI’ (variety.com)
submitted 5 months ago by to c/technology@lemmy.world
72 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 4 points 5 months ago (4 children)

Ok so i think i do all of these things and would just describe them as "other ways to prompt and LLM" - i think the nuance youre shooting for here is that using these methods you are "pre-preparing" the prompt - not thinking about it at prompt-time and thus likely to miss stuff.

e.g. Feeding a TODO is just the same as copy-pasting that todo in as a prompt.

Have I understood you correctly?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 5 months ago* (3 children)

    No, it's not the same as copying and pasting the TODO into a prompt. Embedding the TODO in code instead of the prompt reduces tokens burned and increases accuracy because it's observing the TODO in context. Sure you can write more prompting to provide that context, but it still won't be as accurate. The less context you provide via prompting and instead provide more context through automatic deterministc feedback the better the results

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 2 points 5 months ago (2 children)

    Okay so now I think you're describing the behaviour I take for granted with the harness i.e. Claude Code.

    Having good repo readiness through a good agents/claude.md file + tests + docs means the LLM is able to read more files into its context.

    It never occurred to me that anyone would prompt in isolation of their repos but I guess thats exactly what it was like for me last year when I was just feeding ChatGPT prompts away from the repo.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 5 months ago (1 child)

    Yes, code harnesses help by providing deterministic feedback like with a language server and reduce the amount of prompting requirements. I guess I should have led with that example 😅

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 5 months ago

    Gotcha...I've always struggled to pick up the vocabulary around technical concepts - I guess ive just never prioritised it, and now this whole new field has materialised with a whole new vocabulary to go along with it! I get the tech. The words are my achilles heel.

  • permalink
  • fedilink
  • source
  • parent