Interacting with LLMs in a post-chatGPT world

Currently, there seems to be something new/interesting being released daily - along with an uptick in concerns about alignment/safety. For this MeetUp, we are revisiting Large Language Models from the perspective of building applications that use LLMs to do a variety of tasks.

Talks:

Going beyond a single prompt - Martin Andrews

As the LLM world opens up (notably with the release of the Llama models - but not forgetting the FLAN-UL2 series), there has been a surge in new ideas about how models can be encouraged to make use of tools, self-reflect, and self-direct. Martin will be explaining what these ideas are building on, what's new, and some challenges ahead.

Autonomous AI + Advanced LangChain - Sam Witteveen

As things are moving at the speed of light we are seeing the introduction Autonomous AI with LLMs which go far beyond chat and QnA. Sam will look at some of these systems and how you can build similar things in LangChain.

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, we're sure there are lots of people who would be interested to hear what you've been playing with. Please suggest yourself here :
https://www.meetup.com/Machine-Learning-Singapore/suggestion/