Gen AI Demos & Tech Talk
Details
This week will be starting an hour early. 6pm @ 3000 El Camino Real, 5 Palo Alto Square Suite 400, Palo Alto, CA 94306 with some light drinks and snacks provided by Procopio. See https://www.procopio.com/ for your startup's legal needs.
Agenda:
6:00pm: Meet & greet
6:30pm: Project demo (Connor Fahy)
6:45pm: Talk & demo (Brian hart)
7:00pm: Tech talk + Q&A (Ryan Michael)
7:30pm: Open discussion
Connor Fahy - Project demo: *http://hyperthetical.dev*
No-code programming tool for building smarter bots with LLMs like ChatGPT.
Brian Hart - Talk & demo: Founder of Mind Machine Learning
Providing foundation models with virtual embodiment and senses for digital twin and virtual assistant applications.
Tech Talk:
Ryan Michael - From Generic To Genius: Personalize Generative AI
Generative AI has already demonstrated immense value, but systems like ChatGPT don’t know anything about who we are as individuals. At Kaskada, we have developed a compute engine to help LLM’s understand who they’re talking to and what they’re talking about. Kaskada does this by augmenting prompts with real-time contextual information and making it easy to recreate the context of past prompts, significantly accelerating the prompt engineering process.
In this talk, we introduce the abstraction that makes this possible: the concept of timelines. Timelines can be interpreted as a history of changes or as snapshots at specific time points. Discover how to:
- Simplify the examination of historical and recent events, integrating well with modern architectures.
- Create histories, snapshots, event-based aggregations, and sequence reasoning with timeline abstractions.
- Enables personalized generative AI agents that adapt to individuals' needs in real-time.