#136 - Designing Generative AI at Notion with Linus Lee

Awkward Silences

AI is a big part of Notion's strategy for the future of knowledge work, and they're exploring ways to use AI to make people's lives easier.

Linus Lee, a Research Engineer at Notion, spends his time researching and learning about AI—how users interact with it, the challenges of building trustworthy AI systems, and its - potential to help people work more effectively.

In this episode of Awkward Silences, he sits down with Erin and Carol to discuss Notion’s approach to designing interfaces for Generative AI tools.

Tune into this episode to learn more about the challenges of instructing AI, the importance of user feedback to the AI design process, security considerations, use cases, and more.

Highlights:

[00:05:03] Tools Linus is excited to see come to market

[00:06:50] Generative AI and its function at Notion

[00:10:22] Recognizing AI is useful versus finding the use cases for it

[00:13:58] Lessons from the Notion design process

[00:22:09] Breadth versus depth in workflows

[00:26:10] Learning about models in the wild

[00:28:52] Security considerations with AI products

[00:32:13] Understanding the difference between AI generated and human written text

[00:36:34] Should we be scared of AI?

About Our Guest

Linus Lee is a Research Engineer at Notion, prototyping new software interfaces for augmenting our collaborative work and creativity with AI. He has spent the last few years experimenting with AI-augmented tools for thinking, like a canvas for exploring the latent space of neural networks and writing tools where ideas connect themselves. Before Notion, Linus spent a year as an independent researcher in New York City.