Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

youtube.com

Post reply on HN
Print view View original

51–60 of 249 posts

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#51

Post by natch »

mindfulplay wrote: post #22

Just listening to this talk scares me. The amount of errors - even in a seemingly normal, sunny day - is mind boggling to think people trust this crap. How can we rely on the output of eight cameras? This is not a kid's science project. It's all fancy neural networks until someone dies. Pretty callous and Silicon valley-mindset for such an important and critical function of the car. Will never buy a Tesla after havin…

It does require human supervision while driving.

Tesla makes this very clear.

It's also all over the Internet.

But there will always be people who do not get this.

Those people should not drive Teslas, or pretty much any modern car for that matter.

If you are under the impression that you would be relying on this system to drive the car, then I agree you should not get a Tesla.

Of course full self driving is coming at some point, but that's a conversation for another day. Meantime Tesla is making steps toward it very incrementally with things like the "stop mode" rolling out right now.

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#52

Post by boulos »

karpathy wrote: post #42
soulslicer0 wrote: post #18

Earlier quoted context omitted.

lol i just did the interview and failed. had to find shortest path between tesla chargers. all in C++. completed it but failed

Very likely not for the positions above! (they all focus on Python)

Slightly off-topic (but related to the side thread where people didn’t realize you went to Tesla): your HN about still says you’re at OpenAI :).

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#53

Post by karpathy »

boulos wrote: post #52
karpathy wrote: post #42

Earlier quoted context omitted.

Very likely not for the positions above! (they all focus on Python)

Slightly off-topic (but related to the side thread where people didn’t realize you went to Tesla): your HN about still says you’re at OpenAI :).

oops, thank you, fixed :)

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#54

Post by f00_ »

soulslicer0 wrote: post #18
timzaman wrote: post #11

His team is hiring; https://www.tesla.com/careers/job/software-engineerdeeplearn... https://www.tesla.com/careers/job/machine-learninginfrastruc... https://www.tesla.com/careers/job/machine-learningscientista...

lol i just did the interview and failed. had to find shortest path between tesla chargers. all in C++. completed it but failed

Could you have just used dijkstra or breadth first search?

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#55

Post by perl4ever »

ajross wrote: post #50
perl4ever wrote: post #47

Earlier quoted context omitted.

"It's also mind boggling to think we currently trust organic tissue to do this crap, some of which is bathed in psychoactive chemicals." The appropriate standard for self-driving cars is a sober professional driver, not the average idiot on Saturday night. It isn't unusual for a driver to go a million miles without an accident, when that's their job.

No, the appropriate standard for a self-driving car is the driver they replace. If they're safer than whoever would have been driving (be it on a saturday night or not) then they're a net win. Right now the average idiots are buying more Teslas than mail carriers and cab drivers, though that might change I guess. Numbers are numbers.

A Tesla owner could ride in a cab or on a bus, though. On average, it seems like without a Tesla they would be at least minimally more likely to.

You seem to be implying that cab drivers are the only people who ride in cabs.

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#56

Post by natch »

sdan wrote: post #12

Really liked this talk. Looks like they are really nicely orchestrating workloads and training on numerous nets asynchronously. As a person in the AV industry I think Tesla's ability to control the entire stack is great for Tesla... maybe not for everyone who can't afford/doesn't have a Tesla.

>maybe not for everyone who can't afford/doesn't have a Tesla.

Affordability is not as much of an issue as some make it out to be. Cost-wise it's like owning a Camry or an Accord, if you go for the lower end models. If you mean not everyone can afford a new car, then sure I agree with you.

Edit: if you think I'm wrong about this, please explain or ask me to clarify anything?

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#57

Post by ars »

ajross wrote: post #50
perl4ever wrote: post #47

Earlier quoted context omitted.

"It's also mind boggling to think we currently trust organic tissue to do this crap, some of which is bathed in psychoactive chemicals." The appropriate standard for self-driving cars is a sober professional driver, not the average idiot on Saturday night. It isn't unusual for a driver to go a million miles without an accident, when that's their job.

No, the appropriate standard for a self-driving car is the driver they replace. If they're safer than whoever would have been driving (be it on a saturday night or not) then they're a net win. Right now the average idiots are buying more Teslas than mail carriers and cab drivers, though that might change I guess. Numbers are numbers.

If you like numbers, then you'll like this one: Humans achieve 7 9's of reliability when driving a car, as measured for fatalities by time, or 8 9's if you measure by miles.

I've yet to see a computer just stay up that long, never mind actually doing anything the whole time.

(If you use the collision rate instead, the numbers are about 500 times worse - but that's still quite a lot of 9's.)

People have this fixed thought that humans are terrible drives. They are not! Computers have their work cut out for them to exceed the reliability record humans have set.

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#58

Post by boulos »

karpathy wrote: post #53
boulos wrote: post #52

Earlier quoted context omitted.

Slightly off-topic (but related to the side thread where people didn’t realize you went to Tesla): your HN about still says you’re at OpenAI :).

oops, thank you, fixed :)

As long as you’re here, I’d love to get an updated PyTorch vs TF from you in the sibling thread as payment :).

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#59

Post by matz1 »

mindfulplay wrote: post #22

Just listening to this talk scares me. The amount of errors - even in a seemingly normal, sunny day - is mind boggling to think people trust this crap. How can we rely on the output of eight cameras? This is not a kid's science project. It's all fancy neural networks until someone dies. Pretty callous and Silicon valley-mindset for such an important and critical function of the car. Will never buy a Tesla after havin…

How many actually dies? Do you have the statistic?

Re: Andrej Karpathy talks about how Tesla's NNs are structured and trained [video]

#60

Post by ars »

soulslicer0 wrote: post #18
timzaman wrote: post #11

His team is hiring; https://www.tesla.com/careers/job/software-engineerdeeplearn... https://www.tesla.com/careers/job/machine-learninginfrastruc... https://www.tesla.com/careers/job/machine-learningscientista...

lol i just did the interview and failed. had to find shortest path between tesla chargers. all in C++. completed it but failed

How does that work? Where you given the algorithm to use? Or was it really a data science question, rather than a programming question?
Post reply on HN