Thread by @mattshumer_

Here's a simple guide to set up your OpenAI Playground for day-to-day use, as a (better!) replacement for ChatGPT.

I've been getting so many questions about this, so hopefully this is helpful!

Read on:

https://twitter.com/mattshumer_/status/1700665650492932191

First, why would you want to use the Playground over ChatGPT?

- Greater system prompt/behavior control
- Save multiple system prompts
- Temperature/creativity control
- Longer outputs for reasoning prompts/working with longer text
- Non-nerfed models :)
- Edit all messages

Etc.

So how can you set it up in a way that makes it as frictionless as using ChatGPT?

We'll do this by creating a 'preset' that enables instant access to an optimized setup.

Let's get started:

First, go to .

Make sure you're in Chat mode and select GPT-4, or GPT-4-32K, if you have it! platform.openai.com/playground/

Next, set temperature to 0.4. I find this is a good starting point for most use-cases, and you can adjust from there for each use-case.

Increase maximum length to enable longer outputs than ChatGPT offers.

For GPT-4, do 3000. For GPT-4-32K, set it to 8000.

After that, paste your system prompt here.

Here is a useful system prompt if you don't yet have one:

https://twitter.com/mattshumer_/status/1701634323370094756

Finally, press 'Save' and save the preset with a name you'll remember.

Then you can take the link of the page and bookmark it to access this preset whenever you need help from AI!

Using this setup will 10x what you're able to do with OpenAI models.

I hope you find this helpful!