As an Experienced LLM User, I Actually Don't Use Generative LLMs Often | Max Woolf's Blog

For many users ChatGPT is the interface for LLM, but the OpenAI API is a much more powerful way to interact.

To that end, I never use ChatGPT.com or other normal-person frontends for accessing LLMs because they are harder to control. Instead, I typically access the backend UIs provided by each LLM service, which serve as a light wrapper over the API functionality which also makes it easy to port to code if necessary. Accessing LLM APIs like the ChatGPT API directly allow you to set system prompts which control the "rules" for the generation that can be very nuanced. Specifying specific constraints for the generated text such as "keep it to no more than 30 words" or "never use the word 'delve'" tends to be more effective in the system prompt than putting them in the user prompt as you would with ChatGPT.com.

This is the capability I tapped into for the Weekly Thing. And now that I have an easy bridge to hit the OpenAI interfaces with Shortcuts I have a super simple way to create logical "agents" (a stretch) that I can easily instantiate and access from my phone whenever I want. Crazy stuff.