AI How To: Advanced LLM Prompting

Поділитися
Вставка
  • Опубліковано 10 гру 2024

КОМЕНТАРІ • 18

  • @kevinc.7730
    @kevinc.7730 4 місяці тому +2

    This is awesome man. I started following shortly after the original chat-gpt hype, and have been patiently waiting for this type of implementation. Can't wait to see where it goes as speed/accuracy/context length improve. Well done

  • @infocyde2024
    @infocyde2024 4 місяці тому +1

    I will look through your repo, lot's of good stuff in here.

  • @michaelfloyd2525
    @michaelfloyd2525 4 місяці тому +1

    you are my AI Engineering GOAT

  • @webdancer
    @webdancer 4 місяці тому

    This is awesome. Thanks for sharing. That spec & planning steps can be leveraged for other areas as well.

    • @realmckaywrigley
      @realmckaywrigley  4 місяці тому

      Chaining those 3 steps is super useful on anything that requires an LLM to do “reasoning”. Try it on math for example - great results!

  • @boggledeggnoggler5472
    @boggledeggnoggler5472 4 місяці тому

    Would be awesome if you could include examples of helpful PRs this setup has generated for you

    • @realmckaywrigley
      @realmckaywrigley  3 місяці тому +1

      Will probably do a follow up once our system is a little more polished!

  • @vitalis
    @vitalis 4 місяці тому +1

    Gonna save this, till I get to this level of knowledge where I leverage a framework like this. Currently I'm just trying to find an automated way to preprocess epub data to increase LLM reasoning and problem solving.

  • @aurelienv5498
    @aurelienv5498 4 місяці тому

    Good job. Need to add openrouter support =)

  • @DonionTech
    @DonionTech 3 місяці тому +1

    why use xml tags over json output?

    • @realmckaywrigley
      @realmckaywrigley  3 місяці тому

      JSON output/function calling tends to result in lower performance for tasks that require higher levels of reasoning like code generation.

    • @DonionTech
      @DonionTech 3 місяці тому +1

      @@realmckaywrigley do you have any resources that go over this topic or is this based on your experience?

    • @DonionTech
      @DonionTech 24 дні тому

      So for anyone who may read this. There are a couple of reasons why you might want to use XML tags over JSON output.
      1. Well trained on XML tag's
      Some models are trained on XML tags explicitly. Claude for example has a good understand of XML tags. Using XML in the input will result in better understanding of the prompt and result in better structured outputs.
      2. No json mode or malformed json outputs
      If a model doesn't have the ability to output in json or the outputs are sometimes malformed. Its often better to output using XML tags. In my testing LLM's have an easier time generating and formatting XML vs JSON.
      3. Ability to "think" and output a structured response in one prompt
      I use to use one model to generate the content and then another to format into JSON. It's cheaper and faster to use tags to generate the content and then provide an XML schema that you can parse all in one response.
      Example output might look something like this:
      Thoughts
      Unique Name
      A detailed description that I will parse later

  • @AhmedMekallach
    @AhmedMekallach 4 місяці тому

    Only three step needed to get functional code output?

    • @realmckaywrigley
      @realmckaywrigley  3 місяці тому

      Depends on how complex your workflow is. Very case dependent, but it's a good place to start experimenting from.

  • @abhijayrajvansh
    @abhijayrajvansh 4 місяці тому

    alright!

  • @michaeldeathless
    @michaeldeathless 4 місяці тому

    Thanks for all your content! I have a business proposition for you. How can I get in touch?

    • @realmckaywrigley
      @realmckaywrigley  3 місяці тому

      Hi, Michael! Unfortunately right now I'm a bit swamped and not open to business proposals at the moment.