How I use AI
Consider this a work in progress.
These are the tips that I often share with my clients and colleagues to help them get the best results with AI. They come from my personal experience engineering context for Large Language Models.
Use different models
The field is moving fast. ChatGPT released around 2 years ago. New models release every couple months. You want to be able to leverage the best tools.
Don't restrict yourself to a single tool/LLM. Try everything. My personal favorite LLM client is LibreChat because it allows to me to have a single app, but be able to interact with any models.
By using different models, you learn what they are good at and not. This is key to getting the best results—choosing the right model.
Engineer context
Garbage in -> garbage out. Elevate the quality of your inputs, to get the best outputs.
Context is essential:
- too little = generic output
- too much = lower prompt adherence (see context rot)