Interfacing with AI, with Linus Lee of Notion AI

50 snips

Mar 20, 2024

Linus Lee from Notion AI discusses innovative interfaces for text and image manipulation, the future of AI reasoning capabilities, and the importance of failure analysis and model merging in AI development. The podcast explores practical AI tools like PyTorch, advancements in language models, and the societal implications of AI advancements.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Manipulating Latent Spaces

Language and image models can be manipulated in their latent spaces for semantic control rather than pixel or token level changes.
This approach enables new ways to edit and generate content by blending features in meaningful vector space rather than traditional representations.

INSIGHT

Spatial Interfaces for Text Editing

Visualization of high-dimensional latent spaces can be done using 2D slices mapped to meaningful attributes like sentiment or topic.
Interactive spatial interfaces allow users to explore and manipulate semantic features intuitively, preserving edit histories.

ADVICE

Prototype for Insight and Utility

Prototype interfaces early to understand their utility and identify improvements.
Use prototypes both for research insight and for practical daily applications when technologies mature.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Hello, and welcome back to the Cognitive Revolution!

Today my guest is Linus Lee, AI product leader at Notion and AI explorer extraordinaire.

I have followed Linus online for a couple of years now, fascinated by his many groundbreaking projects and unique way of thinking about AI systems. From creating novel interfaces that visualize and manipulate generative models in their latent space, to developing techniques for semantically editing text and images, Linus has been a pioneering tinkerer.

In this wide-ranging conversation, we dig into the details of how Linus goes about his explorations. He shares his toolkit, from PyTorch as a foundation to the custom tools he's built over time for data visualization, model evaluation, and rapid experimentation. We discuss the importance of spending time with data and failure cases, and the value of building your own tools to deeply understand the problems you're trying to solve.

Linus also offers his perspective on the current capabilities of language models, and where he sees the biggest opportunities for improvement. Beyond hallucination reduction, instruction following, and cost efficiency, he emphasizes the need for better general reasoning as a longer-term goal.

We speculate about the future, considering scenarios like models communicating with one another via high-dimensional embeddings, techniques to connect latent spaces across modalities, and the societal implications as AI capabilities continue to advance. Linus articulates a vision centered on amplifying rather than replacing human intelligence, a principle he believes should guide the development and deployment of AI-powered products.

Throughout this episode, Linus demonstrates the curiosity, resourcefulness, and thoughtfulness that have made him such an influential figure in the AI community. His work inspires us to engage more deeply with these systems, to build the tools we need to understand them, and to steer their development in a direction that deepens rather than diminishes human creativity and agency.

As always, if you find value in the show, please share it with others who might appreciate it. Particularly right now as we are establishing the new feed, a tweet or a comment on Youtube would be especially valuable.

And of course, we invite you to reach out with feedback or suggestions on our website, cognitiverevolution.ai

Now, please enjoy this deep dive into the art and science of exploring AI systems with Linus Lee.