Autonomous Agents with LLMs

Continuing the theme of something new/interesting being released daily - this month we look at what models, systems and techniques have come out recently related to code and reasoning tasks.

Talks:

"Building Advanced Autonomous Agents for Real World Use" - Sam Witteveen

In this talk Sam will highlight some of the best practices, architecture patterns and techniques of building and deploying agents for multiple use cases. He will demo a number a Email Agent as well as an Information Gathering Agent.

Lightning Talk - Ming Liang Ang

We wanted to make sure we could extract a talk from Ming Liang Ang before he leaves for a PhD position in London, so he'll be talking about Diffusion Models for Bayesian inference (or thereabouts).

"Open-Endedness and Large Language Models" - Martin Andrews

Now that LLMs have become significantly more capable, it makes sense to start to experiment with them in more open-ended domains. Martin will present some highlights from this exciting new area, which encompasses game-play, evolution and creativity.

***

Talks will start at 7:00pm and end at around 8:30pm, at which point people normally come up to the front for a bit of a chat with each other, and the speakers.

As always, we're actively looking for more speakers - both '30 minutes long-form', and lightning talks. For the lightning talks, we welcome folks to come and talk about something cool they've done with kears_core, TensorFlow, PyTorch, JAX and/or Deep Learning for 5-10mins (so, if you have slides, then #max=10). We believe that the key ingredient for the success of a Lightning Talk is simply the cool/interesting factor. It doesn't matter whether you're an expert or and enthusiastic beginner: Given the responses we have had to previous talks, we're sure there are lots of people who would be interested to hear what you've been playing with. If you're interested in talking, please just introduce yourself to Sam or Martin at one of the events.