Adrien Treuille — Building Blazingly Fast Tools That People Love

Topics covered
Popular Clips
Questions from this episode
- Asked by 246 people
- Asked by 176 people
- Asked by 150 people
- Asked by 66 people
- Asked by 58 people
- Asked by 48 people
- Asked by 34 people
- Asked by 26 people
- Asked by 9 people
Episode Highlights
Foldit
Adrien shares the story behind Foldit, a game designed to tackle the challenging problem of protein folding. He explains how the game transformed a complex scientific issue into an engaging activity that attracted over a million participants worldwide. This crowdsourced effort led to significant scientific insights, demonstrating the power of human intuition in solving computational problems 1.
Over a million people contributed to this really profound scientific problem all over the world.
---
Adrien emphasizes that the game's success was not just about beating computers but about fostering a community that generated innovative ideas and shifted the game design 2.
Eterna
Following Foldit, Adrien developed Eterna, a game focused on RNA folding. Unlike Foldit, Eterna used high-throughput synthesis to build molecules designed by players, integrating real-world experiments into the gameplay. This approach allowed players to contribute to cutting-edge RNA research, including efforts related to COVID-19 3.
The real innovation in Eterna is that rather than just do everything in simulation on a computer, we were actually using high throughput synthesis to build the molecules being designed by the players.
---
Adrien notes that the human element in these games led to unexpected scientific discoveries, such as identifying stable RNA motifs, which have yet to be fully automated by machines 4.
Related Episodes


Adrien Gaidon — Advancing ML Research in Autonomous Vehicles
Answers 383 questions

Building the future of collaborative AI development with Akshay Agrawal
Answers 383 questions

Hamel Husain — Building Machine Learning Tools
Answers 383 questions

Piero Molino — The Secret Behind Building Successful Open Source Projects
Answers 383 questions

Transforming Search with Perplexity AI’s CTO Denis Yarats
Answers 383 questions

Ines & Sofie — Building Industrial-Strength NLP Pipelines
Answers 383 questions

Luis Ceze — Accelerating Machine Learning Systems
Answers 383 questions

Richard Socher — The Challenges of Making ML Work in the Real World
Answers 383 questions

Nicolas Koumchatzky — Machine Learning in Production for Self-Driving Cars
Answers 383 questions

Angela & Danielle — Designing ML Models for Millions of Consumer Robots
Answers 383 questions

Jeremy Howard — The Story of fast.ai and Why Python Is Not the Future of ML
Answers 383 questions

Accelerating drug discovery with AI: Insights from Isomorphic Labs
Answers 383 questions

Dominik Moritz — Building Intuitive Data Visualization Tools
Answers 383 questions

Will Falcon — Making Lightning the Apple of ML
Answers 383 questions

Emad Mostaque — Stable Diffusion, Stability AI, and What’s Next
Answers 383 questions













