Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

Josh Pitzalis

www.jxsh.io/atom/
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 10

  1. Generating Test Datasets with Effect

    (Josh Pitzalis)

    You have written a prompt.

  2. Structured Data with Effect

    (Josh Pitzalis)

    Suppose we are building a web app that generates AWS EventBridge rules.

  3. Response Streaming with Effect

    (Josh Pitzalis)

    A user submits a question, and somewhere in our program LanguageModel.generateText sets off to fetch the answer.

  4. Temperature with Effect

    (Josh Pitzalis)

    Suppose we're building a brainstorming machine.

  5. System Prompts with Effect

    (Josh Pitzalis)

    Suppose we are building a math tutor chatbot.

  6. Multi-Turn Conversations with Effect

    (Josh Pitzalis)

    Before we build anything of consequence, you must internalise an inconvenient truth: the Claude API remembers nothing.

  7. Making an LLM Request in Effect TS

    (Josh Pitzalis)

    Here is an LLM request written with the Anthropic SDK the way most TypeScript developers would. const client = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY!

  8. Trusting your LLM-as-a-Judge

    (Josh Pitzalis)

    The problem with using LLM Judges is that it's hard to trust them.

  9. Setting Up Your First Eval with Typescript

    (Josh Pitzalis)

    One big barrier to testing prompts systematically is that writing evaluations usually requires a ton of setup and maintenance.

  10. Crafting a Solid First Prompt

    (Josh Pitzalis)

    In early 2024, I ran an AI-enablement workshop with iFeel, a company that provides online mental health and wellbeing support for employees, to help them understand how tools like ChatGPT can be utilised at work.