We compare prompt chaining, with an introduction to langchain.ai, and why that vs a plugin.

We review 5 LLMs in 5 minutes, plus an LLM Directory.  For the visuals, as we look at representative websites, check out the YouTube version: https://www.youtube.com/watch?v=1WN47vFWI4Q&list=PL3y876l-nINjAq1kFO7DOZd1AiKDWhaWT&index=1

We cover token distillation, using ChatGPT 3.5 to reduce the tokens of a previous response, which should be extremely useful when paying for more expensive APIs like ChatGPT-4

To see the screen, check the youtube version: https://www.youtube.com/watch?v=VxEVvVUnPLk&list=PL3y876l-nINjAq1kFO7DOZd1AiKDWhaWT&index=2

In this I look at whether this is the early days of AI or some significant plateau. For evidence, we look at both a technical piece of evidence on training performance, as well as a recent announcement from Databricks to try to answer the question

A Friday fun-day light-hearted bake-off between Google Bard and ChatGPT, playing with some prompts.

AI Everyday #2 - Matt discusses OpenAI announcing the ChatGPT Plugin architecture.

AI Everyday #1 - Matt recaps the keynote from nVidia GTC.