Let's Talk about AI - LLM part 1

After our last event, the feedback was clear: folks are really interested in talking and learning more about LLMs — and how we can bring them into our own workflows. But before we get to using them well, we need a solid understanding of how they actually work.

So this session goes back to the roots. We'll start with how machines first learned to handle sequences — recurrent networks, LSTMs, and GRUs — and the tricks they used to "remember" context, plus where they hit their limits. From there we'll follow the breakthrough that changed everything: attention and the Transformer, and how that architecture opened the door to the GPTs and LLMs we all rely on today.

• The goal is intuition first, plain English, with enough under-the-hood detail to make the "oh, that's why it works" moments click. No deep learning background required — just curiosity.
• Once we've got the foundation down, future sessions can dig into the fun part: actually putting these models to work.

Feel free to drop any questions about AI in the comments below — we'd love to fold them into the discussion!