Join us for the AI edition of Google I/O Extended 2023 Seattle, co-located with AI Dev Day (Seattle) to discuss the Generative AI, LLMs technologies and deep dives.
Google I/O Extended is a global series of events that brings the AI developers community together to learn AI technologies through hands-on workshops, tech talks, and networking, in which you have the chance to learn about the latest Google technologies, connect with other developers, and get inspired to build the future.
In addition to the tech talks, there will be plenty of opportunities to network with AI developers, live demos, AI community showcases, and career opportunities.
- 4:30pm~5:30pm: Checkin, food/drink and networking
- 5:30pm~8:00pm: Tech talks
- 8:00pm: open discussion, mixer
Tech Talk 1: What is new in Generative AI at Google
Speaker: Laurence Moroney, AI Advocacy Lead @Google
Abstract: LLMs are capturing the imaginations of people around the world. We are excited to share a new suite of tools that make it easy for developers to build on top of our best models. In this keynote, we will introduce tools and APIs you can use that equip computers with the ability to comprehend and generate natural language with a kind of nuance and fluidity that was never possible before.
Tech Talk 2: Working with LLMs at Scale
Speaker: Yujian Tang, Developer @Zilliz
Abstract: we’ll introduce LLMs and two main problems they face when it comes to production: high cost and lack of domain knowledge. We then introduce vector databases as a solution to this problem. We cover how a vector database can facilitate data injection and caching through the use of vector embeddings.
Tech Talk 3: Generative AI and Program Synthesis
Speaker: Daniel Goncharov, Google Developer Expert in ML
Abstract: This session aims to uncover how Gen AI and program synthesis are reshaping the landscape of coding. We will highlight significant advancements powered by Google Palm and ChatGPT, and provide an insightful overview of influential papers from thought leaders at Princeton, Microsoft, and DeepMind.
Lightning Talk 1: Towards Effective LLM Observability
Speaker: Cam Young, Solutions Architect @Arize AI
Abstract: In this session, we will demonstrate how to leverage LLM observability to evaluate LLM responses, pinpoint where to improve with prompt engineering, and identify fine-tuning opportunities using vector similarity search.
Lightning Talk 2: Monitoring LLMs in Production
Speaker: Sage Elliott, Developer @WhyLabs
Abstract: In this session, we will show a scalable and privacy-centric approach to LLM Observability using LangKit, an open-source toolkit for monitoring LLMs. See how easy it is to detect toxic language, sentiment, jailbreaks, sensitive data leakage, and hallucinations in any LLM (LangChain, HuggingFace, MosaicML, OpenAI, Falcon, etc.)
Husky Union Building (Lyceum Hall) at UW. Google Map.
- Direction: follow the Google map.
- Parking: central parking garage, specifically in the C3 area. Exit through the Kane Hall parking exit. 2-minute walk from the Kane Hall parking exit to the Hub building.
- Car pool: post in the community group on slack (#seattle channel)
We will raffle winners for prizes (books, swags, chromebooks) during the event. To enter the lucky draw, "comment" the post on LinkedIn: LinkedIn Post
Community on Slack
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #seattle channel)
- Future Builders