How an AI Researcher Uses ChatGPT and Notion AI
Linus Lee wants to bring the focus back to human agency when we turn to AI for creative work
Sponsored By: Tnoc
For all the software engineers and engineering managers, say goodbye to the headache of provisioning quality test data. With Tonic, you can effortlessly keep your staging in sync with production using realistic test data generated from your actual production data. It's a seamless solution for maintaining data integrity and efficiency. Discover how with a simple click.
TL;DR: Today we’re releasing a new episode of our podcast How Do You Use ChatGPT? I go in-depth with Notion research engineer Linus Lee on how he uses ChatGPT and Notion AI to maximize creative control. Watch on X, Spotify, or YouTube .
You might think that being an AI researcher would mostly involve solving complicated programming problems and thinking through mathematical equations. Instead, a big part of the job is rewriting parts of your prompts in ALL CAPS in order to make sure the AI model you’re working with follows your directions. “All caps works!” Linus Lee told me in this interview. “If you look at OpenAI's system prompts for a lot of their tools, all caps works.”
Linus is a research engineer at Notion who works on its AI team, prototyping new experiences, like a Q&A chatbot. He is a deep thinker who is obsessed with building AI that enables human creativity and agency. He came on the show to talk about how AI might augment our thinking, how he thinks about prompting to get the best results, and how he uses ChatGPT and Notion AI in his work and life.
I first interviewed him a year ago, when he showed off dozens of AI prototypes he’d been building to try to understand the future of this technology. Our latest interview is a mixture of theory and practice. Linus talks about how the tools we use shape the work we can create and what the future of AI-driven interfaces might be. We watch him demo personal tools he’s built, like an AI chatbot that he communicates with over iMessage. And we peek over his shoulder to see his chats with ChatGPT to understand how he talks to it to get the best results.
Tonic is revolutionizing the way teams handle test data. By transforming sensitive production data into safe, realistic test data, Tonic ensures your pre-prod environments are always up-to-date and secure. Companies like eBay, Flexport, and Everlywell are already leveraging Tonic to keep their environments fresh and consistent. With Tonic, you can accelerate regression testing, catch bugs quicker, and significantly shorten release cycles. Experience a smoother, more efficient workflow that aligns with your development needs. Ready to transform your data management?
Here’s a taste of what we talk about. Read on for more analysis from me at the bottom.
- Using AI to maximize agency. Linus talks a lot about the ways our tools shape our agency as thinkers and creatives—and how AI might be used to enhance rather than reduce our agency.
- AI as a “thought calculator.” Linus borrows a phrase from the popular tech blogger Simon Willison to illustrate dueling points of view on the ultimate goal of AI: is it meant to be a simulacrum of humans or a “thought calculator,” a way to enhance human imagination and creativity?
- Personal prototypes he’s built. Linus regularly experiments with AI on the weekend. He shows us a chatbot he built that works over iMessage, and a new interface for image generators that gives him much better control over their output.
- Better prompting. We go over simple yet powerful techniques for getting the best answer out of AI models—like starting with general queries first, and repeatedly asking the model to answer the same question.
- Using AI for vibe checks. AI is great for reflecting the vibes of books, people, places—and even files on your computer. Linus talks about how he uses ChatGPT to get quick vibe checks that allow him to make decisions.
- Book recommendations. We pit ChatGPT head-to-head against Notion AI to see which can best capture our reading taste. And just when ChatGPT seems like it’s coming out on top, Linus makes a convincing case for Notion AI’s special skill set as an organizational tool that already knows how its users work.
You can watch the episode on Twitter/X, Spotify, or YouTube. Links and timestamps are below:
- Intro 1:03
- Retaining agency when conversing with AI 4:06
- A personal iMessage chatbot 27:04
- The difference between prompting and prompt engineering 32:49
- “What's the vibe of this file?” 38:48
- Travel recommendations 44:57
- Book recommendations 51:57
- Notion AI's advantage over ChatGPT 56:00
- Using Notion AI at work 1:02:00
- Is GPT-4 getting lazy? 1:09:16
What do you use ChatGPT for? Have you found any interesting or surprising use cases? We want to hear from you—and we might even interview you. Reply here to talk to me!
My take on this show and the episode transcript is below for paying subscribers.
Thanks to our Sponsor:
Thanks again to our sponsor Tonic, the expert in realistic data de-identification. Join a growing list of successful companies who trust Tonic for their test data needs. Embrace a platform that's designed to make your engineering workflows simpler and more effective. With Tonic, you're not just managing test data; you're mastering it. Elevate your data strategy today.