How Sama is Improving ML Models to Make AVs Safer // Duncan Curtis // #307

9 snips

Apr 18, 2025

Duncan Curtis, SVP of Product and Technology at Sama, shares insights from his extensive background in autonomous vehicles and AI. He delves into the crucial role of data annotation in enhancing ML model accuracy for AVs. The discussion addresses the challenges of integrating human input into AI systems and how this can improve safety and efficiency. Curtis also highlights the importance of modernizing data strategies and overcoming bottlenecks in data accessibility, ensuring AI technology can deliver reliable and safe autonomous driving experiences.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

Human Intelligence in Data Labeling

Labeling autonomous vehicle data involves capturing complex scenes with lidar, cameras, and radar.
Human intelligence helps recognize objects consistently, like identifying the same car behind a truck.

ADVICE

Focus on Edge Cases and Bias

Prioritize labeling data that captures edge cases, not just routine driving scenes.
Use metadata to ensure diverse class and condition representation, minimizing bias.

ANECDOTE

Driving Challenges in India

Driving in India involves adapting to unpredictable conditions with animals and varied traffic.
Personal experience showed how internal models change after encountering new road elements repeatedly.

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

Get the app

How Sama is Improving ML Models to Make AVs Safer // MLOps Podcast #307 with Duncan Curtis, SVP of Product and Technology at Sama.

Join the Community: https://go.mlops.community/YTJoinIn Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

Between Uber’s partnership with NVIDIA and speculation around the U.S.'s President Donald Trump enacting policies that allow fully autonomous vehicles, it’s more important than ever to ensure the accuracy of machine learning models. Yet, the public’s confidence in AVs is shaky due to scary accidents caused by gaps in the tech that Sama is looking to fill.As one of the industry’s top leaders, Duncan Curtis, SVP of Product and Technology at Sama, would be delighted to share how we can improve the accuracy, speed, and cost-efficiency of ML algorithms for AVs. Sama’s machine learning technologies minimize the risk of model failure and lower the total cost of ownership for car manufacturers including Ford, BMW, and GM, as well as four of the five top OEMs and their Tier 1 suppliers. This is especially timely as Tesla is under investigation for crashes due to its Smart Summon feature and Waymo recently had a passenger trapped in one of its driverless taxis.

// Bio

Duncan Curtis is the SVP of Product at Sama, a leader in de-risking ML models, delivering best-in-class data annotation solutions with our enterprise-strength, experience & expertise, and ethical AI approach. To this leadership role, he brings 4 years of Autonomous Vehicle experience as the Head of Product at Zoox (now part of Amazon) and VP of Product at Aptiv, and 4 years of AI experience as a product manager at Google where he delighted the +1B daily active users of the Play Store and Play Games.

// Related Links

Website: https://www.sama.com/Tesla is under investigation: https://www.cnn.com/2025/01/07/business/nhtsa-tesla-smart-summon-probe/index.htmlWaymo recently had a passenger trapped: https://www.cbsnews.com/losangeles/news/la-man-nearly-misses-flight-as-self-driving-waymo-taxi-drives-around-parking-lot-in-circles/https://coruzant.com/profiles/duncan-curtis/https://builtin.com/articles/remove-bias-from-machine-learning-algorithmsLook At Your ****ing Data :eyes: // Kenny Daniel // MLOps Podcast #292: https://youtu.be/6EMnkAHmoag

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]Connect with Demetrios on LinkedIn: /dpbrinkmConnect with Luca on LinkedIn: /duncan-curtis

Timestamps:[00:00] Duncan's preferred coffee[00:08] Takeaways[01:00] AI Enterprise Focus[04:18] Human-in-the-loop Efficiency[08:42] Edge Cases in AI[14:14] Forward Combat Compatibility Failures[17:30] Specialized Data Annotation Challenges[24:44] SAM for Ring Integration[28:50] Data Bottleneck in AI[31:29] Data Connector Horror Story[33:17] Sama AI Data Annotation[37:20] Cool Business Problems Solved[40:50] AI ROI Framework[45:11] Wrap up