161–170 of 187 posts
Earlier quoted context omitted.
Too expensive. They also removed radar because of the global chip shortage so they're all in on vision.
> Too expensive. They also removed radar because of the global chip shortage so they're all in on vision. That doesn't make much sense to me. Tesla also needs chips for computer vision.
Earlier quoted context omitted.
Yes. This is exactly what LIDAR is for. This is the reason every single team in the 2007 DARPA Urban challenge that finished the race was equipped with a Velodyne laser. We knew it was a critical enabling technology 14 years ago, and it baffles me Tesla is eschewing it. Tesla's lack of this technology is the main reason I feel they will never achieve what they claim to without a huge breakthrough in AI.
Idk.. animals seem to do fine without a lidar
I find it amusing (and maybe even ironic?) that tools and methods (GPUs and game engines, etc.) whose development was mainly driven by gaming and entertainment (rather frivolous use cases) now find applications in a much more "serious" domain with a potential to revolutionize our lives.
Earlier quoted context omitted.
They were supposed to do coast to coast self driving years ago according to these hype videos https://www.digitaltrends.com/cars/tesla-coast-to-coast-auto... Hard to take them seriously given how much hype they generate each year.
Accurate hardware/software development timelines are an unsolved problem. To me, the question is: is the technology getting better over time? And from what I've seen I would answer that question with a resounding yes.
Then why is it sold as a $10,000 full self driving package?
Bottom line, robots coming soon. He's slowly building out the roadmap for the labor pool, transportation, communications system and so on for the colonization of Mars.
They were supposed to do coast to coast self driving years ago according to these hype videos https://www.digitaltrends.com/cars/tesla-coast-to-coast-auto... Hard to take them seriously given how much hype they generate each year.
Earlier quoted context omitted.
Compare it to a horse. No one knows what's going on in the horse's brain. However, we learned to trust it and how to deal with it safely. E.g., blinkers (the devices to limit a horse's peripheral view).
Horse collisions didn't usually end up in death. Horses also weren't sprinting at 65 mph through 8 lane highways.
Earlier quoted context omitted.
> Because for whatever reason (hubris?) Tesla insists on eschewing LIDAR/RADAR for 100% camera based systems. It's a retrofit problem. The moment you admit that you need LIDAR/RADAR, every Tesla on the road loses value unless you're willing to retrofit them all. Comma.ai has sidetracked this issue by basically using the built-in sensors on the vehicles, and there's rumors of a camera-only version for those without ra…
> Comma.ai has sidetracked this issue by basically using the built-in sensors on the vehicles Comma/OpenPilot doesn't work with Lidar anywhere I'm aware of...
Earlier quoted context omitted.
They were supposed to do coast to coast self driving years ago according to these hype videos https://www.digitaltrends.com/cars/tesla-coast-to-coast-auto... Hard to take them seriously given how much hype they generate each year.
When you are doing innovative stuff that's never been done before like FSD it must be near impossible to get an accurate timeline. I guess they maybe need to do a bit of hype for the investors.
Earlier quoted context omitted.
> At the end of the day though, there is no way for me or anyone to audit the neural networks or their training data. How can anyone trust them? By external measurements and statistics. You measure an ML engine by performance. Literally no one anywhere knows how to debug these things by looking inside the model. If it's a "fragile system" then it will be shown to be so in data. At the end of the data, either cars cra…
How can you measure the performance of an ML engine in untested conditions? Tesla's whole goal is to achieve L5 capabilities. That means anywhere in any conditions, which is clearly impossible to comprehensively validate with a finite test set. It's plausible that we could get a long period of acceptable safety before a black swan event suddenly causes deaths because it can't handle smoke, heavy rain/fog, or blizzard…
I agree with you that those techniques won't eliminate errors, but I don't think that's the requirement for L5 - human drivers' errors cause lots of deaths today.
Earlier quoted context omitted.
> You think they are fake collecting data? I suppose they wrote code to create fake uploads from peoples cars. How deep is this conspiracy going. The conspiracy "keeps going" by the simple math of what they claim to collect vs what actually comes off of the cars and is stored. Do you have any idea the bandwidth and storage associated with endless hours of video storage? Where is it all accounted for? Do you think peo…
There are more the 1 million Tesla on the road. And they say they are using 1.5 million clips for the training. How is that even remotely unreasonable? And they are not uploading hours of video at the time. They literally explained in detail how they are sourcing videos, I'm sorry if you didn't pay attention or don't understand it. I have heard a lot of criticism of Tesla from experts, but not a single one questioned…
I realize they explained how they source the videos, which is in direct contradiction to previous claims. Was this your first rodeo?
>Do you have the measure of all Tesla data that went threw cell towers and can prove that they didn't upload a few million clips?
Right, it's now just a few million clips, not billions of miles of footage from multiple cameras, something they had previously claimed. Remember, their vast fleet video data was a massive competitive advantage. The goal posts changed last night. People questioned whether they ever had all that data (your "conspiracy"). Turns out they don't, and don't use it like that. So the "conspiracy" was correct.
>I don't need to guess that you are dickhead.
Lol, what a clown. Hope you get banned.