Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

FSD rewrite will go out on Oct 20 to limited beta

This site may earn commission on affiliate links.
So basically, you just made $#!t up about "bunch of material that many of you would find resembling output of a sensor that Tesla cannot include due to perceived loss of face."

Good to know!

[note: the logic disconnect, Tesla has mules with lidar out in public for whatever reason, and THAT is not embarrassing to them. but having a more powerful radar needs to be "hidden to save face" ]
Seems like you're reading too much into this. Tesla is exploring the use of a higher resolution Detection And Ranging technology.
LIDAR and high resolution RADAR serve the same purpose and their output can be rendered in exactly the same way.
 
  • Like
Reactions: Silicon Desert
If you don't find high resolution radar output similar to lidar output, I can't really help you see.

A visual interlude:
Hi-Res Radar on top, Solid State Lidar on bottom
upload_2020-10-23_13-31-26.png

1920.jpeg
 
Seems like you're reading too much into this. Tesla is exploring the use of a higher resolution Detection And Ranging technology.
LIDAR and high resolution RADAR serve the same purpose and their output can be rendered in exactly the same way.
I am only reading the words that he wrote.
"The vendor appears to be Arbe Robotix and their website has a bunch of material that many of you would find resembling output of a sensor that Tesla cannot include due to perceived loss of face."
 
  • Helpful
Reactions: Todd Burch

This video is pretty good since now we can really see the limitations. Interesting to see:
- It couldn't make either the first left or right turns
- It could not detect the lane markings properly to figure out it's a one-way street
- It missed a car in cross-traffic at a stop sign

I'm still not sure that the cameras are really enough to achieve reliable FSD.
 
That is why I asked the question on here tagging you.

What do you view it like?
Those are your words, not mine.
I already stated they are clearly in desire of an active high resolution sensor. In the past that was lidar that Elon summarily rejected on the then state of things without takign future improvements into account and suddenly it would become a face-loss issue if they were to flipflop on it (same as if Elon decided they'd switch from in-house NN accelerator to some external product).

Now that high resolution radars are appearing they start to have non-lidar options and they seem to be jumping on that.

This is how I see it. You can keep saying I can't really know because no Tesla engineer expressed the desire for lidar in the open (though multiple people left the team and went to companies that embrace lidars (or created their own), mind you, but that's still circumstantial evidence of course) and that I don't work at Tesla and have limited visibility and all of those would be true, but this is how I see this whole thing.
 
I'm still not sure that the cameras are really enough to achieve reliable FSD.

They're not, and they won't be. This rewrite is a good step forward but it's nowhere near safe enough to be released in the wild. It does however create just enough hype for the true believers to justify to themselves paying $10k for it. Go team elon!
 
They seem to be targeting people who have large followings on social media.

Sounds like the street light fallacy - when I drop my keys at night, I only find them near the streetlight, therefore I only drop my keys near streetlights.

There are probably plenty more people who have it, but we're only seeing the most visible people.
 
https://twitter.com/i/broadcasts/1YqJDpgRBZOJV

7 minute or so video of a lady filming herself going to Taco Bell at night with almost no-one else on the roads. Pretty impressive, but also a good look of how far the system still has to go with the major flickering of the visualization at times.
I believe that they will tone down visualizations in production version.
 
They're not, and they won't be. This rewrite is a good step forward but it's nowhere near safe enough to be released in the wild. It does however create just enough hype for the true believers to justify to themselves paying $10k for it. Go team elon!

This from the Bear on Tesla.
I’m going out on a limb, and assume you’re not a software engineer who works on FSD coding.
So, you likely have absolutely no idea if the car is or isn’t capable of FSD. It’s just your opinion, stated as fact. ie; fake info.

You obviously don’t want it to work, but by agreeing to the statement, “the cameras are not enough, and won’t be enough to achieve FSD”, is just like the same old everyday short seller or Tesla hater out there making up fake information to serve their financial purpose.

I’m always interested to know the motivation behind Tesla haters. If you’re a short seller, I get that, if not, what is your motivation for creating fake facts about FSD capabilities that you have no way of knowing ?
 
This from the Bear on Tesla.
I’m going out on a limb, and assume you’re not a software engineer who works on FSD coding.
So, you likely have absolutely no idea if the car is or isn’t capable of FSD. It’s just your opinion, stated as fact. ie; fake info.

You obviously don’t want it to work, but by agreeing to the statement, “the cameras are not enough, and won’t be enough to achieve FSD”, is just like the same old everyday short seller or Tesla hater out there making up fake information to serve their financial purpose.

I’m always interested to know the motivation behind Tesla haters. If you’re a short seller, I get that, if not, what is your motivation for creating fake facts about FSD capabilities that you have no way of knowing ?

Questioning the unknown and making statements based on observations is pretty common behavior from human beings.
 
This from the Bear on Tesla.
I’m going out on a limb, and assume you’re not a software engineer who works on FSD coding.
So, you likely have absolutely no idea if the car is or isn’t capable of FSD. It’s just your opinion, stated as fact. ie; fake info.

You obviously don’t want it to work, but by agreeing to the statement, “the cameras are not enough, and won’t be enough to achieve FSD”, is just like the same old everyday short seller or Tesla hater out there making up fake information to serve their financial purpose.

I’m always interested to know the motivation behind Tesla haters. If you’re a short seller, I get that, if not, what is your motivation for creating fake facts about FSD capabilities that you have no way of knowing ?
Just forget him or put him on ignore. Honestly, I don't think many of us give a care about his motives. Especially in this thread.

Lets keep our eye on the ball, enjoy the moment and not be distracted from the videos being uploaded. There is a lot more to be learned.
 
Questioning the unknown and making statements based on observations is pretty common behavior from human beings.

He wasn’t questioning it. He was confirming a statement that FSD isn’t possible with the cameras they have, without any facts. That’s common for this member here, and very different from questioning the unknown. :)
 
So, you likely have absolutely no idea if the car is or isn’t capable of FSD. It’s just your opinion, stated as fact. ie; fake info... ...what is your motivation for creating fake facts about FSD capabilities that you have no way of knowing ?

Could be the guy is one of the 3 people on Earth who are smarter than Elon, and he truly does "know", with certainty, that FSD is not possible with the current hardware. Not sure that I would lay a bunch of money on that, but it's theoretically possible. :p

RT
 
This video of Autopilot giving space to a biker sharing the road (no bike lane) and partially switching lanes gives a sense of how Tesla will address the long tail. Jump to 3:30 to see the biker maneuver:

It seems like there's no explicit "biker detected, switch lanes" behavior but more of "neural network predicted path goes left," so that's probably also why this early beta can be dangerous. The neural network can suddenly predict a wrong path, and there seems to be fewer restrictions / safeguards on what Autopilot is allowed to control, so this could result in incorrect leaving of the lane.
 
I already stated they are clearly in desire of an active high resolution sensor. In the past that was lidar that Elon summarily rejected on the then state of things without takign future improvements into account and suddenly it would become a face-loss issue if they were to flipflop on it (same as if Elon decided they'd switch from in-house NN accelerator to some external product).

Now that high resolution radars are appearing they start to have non-lidar options and they seem to be jumping on that.

This is how I see it. You can keep saying I can't really know because no Tesla engineer expressed the desire for lidar in the open (though multiple people left the team and went to companies that embrace lidars (or created their own), mind you, but that's still circumstantial evidence of course) and that I don't work at Tesla and have limited visibility and all of those would be true, but this is how I see this whole thing.
Thanks for the explanation, it doesn't quite fit in with your stated moto.
upload_2020-10-23_15-17-20.png


Maybe, "I report what I think I see" would work better?