Tools

Explore

Videos Channels Figures

Atmrix

Tools

Explore

Videos Channels Figures

Atmrix

A

Anthropic Cast

09/06/24

@ Anthropic

In research prompts, I often include many examples to ensure the model can explore a wide range of possibilities, while in consumer applications, I focus on reliability and consistency.

Video

AI prompt engineering: A deep dive

@ Anthropic

AI prompt engineering: A deep dive

09/06/24

Related Takeaways

Anthropic Cast

09/06/24

@ Anthropic

When prompting, I try to give examples that are not too similar to the data the model will see, to avoid overly consistent responses.

Raza Habib

03/01/23

@ Y Combinator

When developing a new large language model product, it's essential to iterate on prompts to find what works best for your specific use case.

Anthropic Cast

04/24/25

@ Anthropic

There's a risk of overcomplicating prompts by trying to anticipate every possible issue the model might face, which can lead to ineffective results.

Y Combinator Cast

05/30/25

@ Y Combinator

When prompts become too complex, using examples can be more effective than trying to articulate every detail in prose, similar to test-driven development in programming.

Kevin Weil

04/10/25

@ Lenny's Podcast

You can enhance your prompting by including examples in your prompt. For instance, provide a problem and a good answer, and then ask the model to solve a similar problem.

Anthropic Cast

09/06/24

@ Anthropic

Reading prompts and model outputs closely helps improve prompting skills; experimentation is key.

Y Combinator Cast

05/30/25

@ Y Combinator

In prompt engineering, it's crucial to provide examples of desired outputs, as this helps the AI reason through complex tasks and improves the overall quality of its responses.

Anthropic Cast

09/06/24

@ Anthropic

It's important to evaluate prompts by testing them in real scenarios, as this can reveal flaws in the prompt design that need addressing.

Anthropic Cast

09/06/24

@ Anthropic

When prompting, it's important to give the model an 'out' for unexpected inputs, allowing it to indicate uncertainty when necessary.