This chapter covers
- Understanding how to access and interact with AI models in the most productive ways possible
- Configuring models to provide the best fit possible for your specific needs
- Using the OpenAI Playground to better understand key tools for controlling AI
Throwing clever prompts at an AI chat interface can definitely produce impressive results. But by ignoring the finer points of model configuration, you’ll be missing out on most of your AI’s potential value. So with this chapter, we’ll begin the process of figuring out which dials to turn and how far to turn them (and which big red button you should absolutely avoid).
Of course, for all I know, by the time you get around to reading this, the whole process might be automated. That blue light gently pulsing on your keyboard that you can’t resist staring at? That would be the brainwave scanner GPT now uses to directly download your innermost goals and desires. Your results are available now.
Accessing GPT models
In case you haven’t yet had the pleasure, most popular interactive AI platforms require you to create an account before trying them out. For OpenAI’s ChatGPT, that’ll happen at https://chat.openai.com/auth/login. Even if you’re asked to provide credit card information, you’ll be given plenty of warning before you’re actually billed. Just don’t ignore those warnings.
Once you’re signed up, the ChatGPT interface is available at https://chat.openai.com/.