Working with LLMs is pretty much like doing a bit of alchemy, especially prompt engineering.

What I want to learn to do:

  1. Communicate with LLMs via API and for batch processing of tasks.

  2. Text Embedding + clustering using LLM.

  3. Making a function call to an external agent/program using LLMs. For example, make it call python symbolic processor.

  4. Retrieval Augmented Generation (RAG) ()

Applications and interesting experiments

  1. Have LLM judge the reliability of its own outcome and raise the most problematic ones.

  2. Get LLMs to draw/modify diagrams in SVG/Tikz

Tips and Tricks

  1. Getting “dill” to work when an LLM object is present in python notebook.