How to think about intelligence
Now that intelligence has become a commodity, how should we think about it?
Few shot prompting beats prompt engineering
A ton of hacks have blown up to try to get better outputs, but the answer was in front of us all along.
LLMs - Serializers, Abstractions and Domain Specific Languages
Shortly after large language models became ubiquitous, developers clamored for abstractions. They yearned for simplicity before they understood the basics.
Staffing Search Tool - RAG/Function Calling
Transformers brought us more than just large language models, they created a ton of new ways to build applications. Here is an example of one powerful use case.