Gradient Dissent: Conversations on AI12 Elo 2020

Anantha Kancherla — Building Level 5 Autonomous Vehicles

As Lyft’s VP of Engineering, Software at Level 5, Autonomous Vehicle Program, Anantha Kancherla has a birds-eye view on what it takes to make self-driving cars work in the real world. He previously worked on Windows at Microsoft focusing on DirectX, Graphics and UI; Facebook’s mobile Newsfeed and core mobile experiences; and led the Collaboration efforts at Dropbox involving launching Dropbox Paper as well as improving core collaboration functionality in Dropbox.

He and Lukas dive into the challenges of working on large projects and how to approach breaking down a major project into pieces, tracking progress and addressing bugs.

Check out Lyft’s Self-Driving Website:

https://self-driving.lyft.com/

And this article on building the self-driving team at Lyft:

https://medium.com/lyftlevel5/going-from-zero-to-sixty-building-lyfts-self-driving-software-team-1ac693800588

Follow Lyft Level 5 on Twitter:

https://twitter.com/LyftLevel5

Topics covered:

0:00 Sharp Knives

0:44 Introduction

1:07 Breaking down a big goal

8:15 Breaking down Metrics

10:50 Allocating Resources

12:40 Interventions

13:27 What part still has lots ofroom for improvement?

14:25 Various ways of deploying models

15:30 Rideshare

15:57 Infrastructure, updates

17:28 Model versioning

19:16 Model improvement goals

22:42 Unit testing

25:12 Interactions of models

26:30 Improvements in data vs models

29:50 finding the right data

30:38 Deploying models into production

32:17 Feature drift

34:20 When to file bug tickets

37:25 Processes and growth

40:56 Underrated aspect

42:34 Biggest challenges

Visit our podcasts homepage for transcripts and more episodes!

www.wandb.com/podcast

🔊 Get our podcast on Apple and Spotify!

Apple Podcasts: https://bit.ly/2WdrUvI

Spotify: https://bit.ly/2SqtadF

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(138)

He's Building an AI That Can't Lie | Dan Klein

"We are going to switch from the problem in AI being that nothing works to the problem being that everything works."Dan Klein has been studying language models for over two decades and is now a profes...

16 Kesä 1h 14min

He Raised $70M to Cure Every Disease With AI | Samuel G. Rodriques, Edison Scientific

Samuel Rodriques left physics because there were no unsolved problems left.Instead, he built an AI scientist named Kosmos to cure every disease, solve aging, and map the human brain.In this episode:Th...

26 Touko 1h 14min

Uber, Nissan, and Mercedes Chose This Self-Driving Startup | Alex Kendall, Wayve

"Every vehicle is capable of driverless operation. That's clearly the steady state of where we're going."Wayve started in a rented house in Cambridge with $1.5M, a car in the garage, and an aim to int...

15 Huhti 45min

Why Netflix, Uber, and Spotify Never Lag: The Database Nobody Talks About | Aaron Katz

"Companies designing for agents, not humans, are going to get a lot of lift."ClickHouse started as an internal tool at Yandex. Today it's the database Anthropic, OpenAI, Meta and Tesla all run on.In t...

31 Maalis 43min

The $64M Bet on an AI That Has to Be Right | Carina Hong, CEO of Axiom

Formal verification already consumes years of human effort.In this episode, Lukas Biewald talks with Carina Hong, Founder & CEO of Axiom, about why verification is becoming the real bottleneck in high...

5 Helmi 50min

What a $42B Software Co. Really Spends on AI Tools

“I don't worry about being replaced by AI. I worry about being replaced by someone who's really good at using AI.”Atlassian has 10,000+ engineers currently split-testing the world’s top AI coding tool...

20 Tammi 1h 7min

Inside the $41B AI Cloud Challenging Big Tech | CoreWeave SVP

The future of AI training is shaped by one constraint: keeping GPUs fed.In this episode, Lukas Biewald talks with CoreWeave SVP Corey Sanders about why general-purpose clouds start to break down under...

6 Tammi 53min

Why Physical AI Needed a Completely New Data Stack

The future of AI is physical. In this episode, Lukas Biewald talks to Nikolaus West, CEO of Rerun, about why the breakthrough required to get AI out of the lab and into the messy real world is blocked...

16 Joulu 20251h