George Hotz: Comma.ai, OpenPilot, and Autonomous Vehicles | Lex Fridman Podcast #31
Why Hacker News recommends it
HN recommends it for Hotz's reasoning on cameras versus lidar and for an opinionated, original thinker's overview of comma and openpilot.
What it is
Lex Fridman's two-hour podcast with George Hotz, founder of Comma.ai, covering openpilot, autonomous driving and Hotz's views on AI and technology.
Recommended by 7 HN commenters across 5 different months, 2019 to 2026.
What Hacker News said
Strong rec mark_l_watson · 2019-08 · on “Camera vs. Lidar”
I strongly recommend Lex Firdman’s recent interview with George Hotz where they covered this topic in some detail [this video]
Strong rec bko · 2020-12 · on “Ask HN: Favorite Podcast Episode of 2020?”
I loved this interview Lex Fridman had with George Hotz. He's very opinionated original thinker with the credentials to back it up. He runs comma.ai, sellers of a device that can plug into many cars and drive for you. [this video]
Strong rec nomel · 2026-01 · on “Open-source self-driving for 325 car models from 27 brands”
There's a few Lex Fridman podcasts with George Hotz, the founder. Highly recommend them: #31 [this video] #132 [LINK] #387 [LINK]
Recommends rmason · 2019-08 · on “Camera vs. Lidar”
I suspect this is yet another story sponsored by the Tesla shorts. Just saw an excellent two hour interview by Lex Fridman of George Hotz and he goes into details why he thinks camera will win over lidar. But he also admits that presently Google is ahead of everyone in the race for level 5, but raises the question of whether they can ever do it economically enough to make money on it? [this video] 2 hours! Money quote is when Lex tells him, ""Some non-zero part of your brain has a madman in it" I'd argue that is true of many of the greatest inventors of our time.
Recommends dumbfoundded · 2019-08 · on “How Uber Got Lost”
I agree. Self-driving cars will take a really long time to emerge. The progress will be gradual. According to George Holtz of Comma ai, great lane-keeping is the first major milestone. The problem with your logic is the connection to Uber. Uber doesn't control the cars their drivers use. Sure they can set restrictions but they never collect actual data that is useful for self-driving. The only data Uber collects is when and where people want to travel. Google & Apple both have this dataset (probably superior) through their map apps. The real data gathering will come in the way Tesla does. Gather data from real-time drivers by putting the necessary sensors in cars you sell. Maybe Uber could f
Recommends czr · 2019-11 · on “Show HN: Autopilot written in Keras for Self Driving Cars”
for specifics, would recommend to simply read the code. for overall context, geohot has done interviews ([0], [1]) and that give overview of comma/openpilot at high level. [0] [LINK] [1] [this video]
Recommends kick · 2020-01 · on “Comma Two Devkit”
[this video] This Lex Friedman interview is pretty explanatory on the topic of responsibility. A couple of highlights, which point to Comma being at minimum more responsible than Tesla: Comma doesn't advertise itself as anything beyond L2, unlike Tesla; Comma doesn't fuck up eye-detection, it refuses to cooperate with a driver who has their eyes off the road.
Cites merryje · 2022-09 · on “On Device Learning”
He was on the Lex Fridman podcast twice. He's definitely an interesting guy. I've been following comma.ai for some time now it's really cool seeing how much they've accomplished. August 2019 - [this video] October 2020 - [LINK]