Prompts and GPT-3

I have been working with GPT-3 for a while now and have had access to the API for weeks now and one thing I've found of importance is writing prompts. It's important to write prompts that provide enough context about the output expected and are also relevant to the environment. I tried lots of things and it is definitely not easy to create prompts for the API. You really need to optimize lots of things to efficiently receive outputs and also to make sure that you don't end up wasting the number of tokens you have.

Providing the API with examples works well but you really need to focus on writing good ones. I've seen that it’s really hard to train the API for specific and complex use cases. For example, the one I am working on. I am using GPT-3 for an app I am working on (Mailroo) and my motive as of now for it is to be able to write good cold emails and sales emails. I definitely need to niche down and select a small and select set of markets in order to successfully gain users and make something worthwhile.

Well, I tried with several templates of sales and it seems I still have a long way to go in writing good enough prompts for GPT-3. I'll keep on improving and making the prompts better to get really good types of outputs in form of emails from the API. I think though that I am at least near a point where the API will provide good enough email output for most of the instances. Let's see, IDK. Hoping for the best.

Well, that’s it for today but here are few interesting examples that I tried with GPT-3.