Code and Reasoning 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:

Models that Write Code - Martin Andrews

Martin's talk will cover code generation models (like CodeT5+, StarCoder and the recent phi-1 work), and VOYAGER (an embodied agent for playing Minecraft, that must write code to actually do tasks). If there's time, maybe we'll also visit the land of TinyStories for further inspiration...

The Current Reasoning Stack: ReAct, Tools, OAI Functions & more - Sam Witteveen

In this talk Sam will go through some of the techniques and systems people are using to get LLMs to reason, make decisions and initiate actions.

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 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.