Search results

You're failing to see the bigger picture here. FSD is part of a comprehensive life safety system, together with Optimus and Neuralink. Should you experience an FSD accident in the near future, you will have your head grafted to an Optimus body and your brain connected to Neuralink, allowing you...

I fail to understand why people are so obsessed with scale right now. The focus right now should be safety, especially since the tech isn't even proven yet. It's like talking about scaling smartphones in 2003. Let's not get ahead of ourselves. The one aspect that everyone obsessed with scale...

You just have to believe Tesla is being truthful and not attempting to mislead by omission. Which should be easy to do.

The solution is so simple that I'm surprised Elon hasn't thought of it yet. Tesla just needs to push an OTA to all its vehicles that makes them drive perfectly, with 0 accidents regardless of driver attention, regardless of what type of road AP/FSD is used on, regardless of whether the driver...

Mobileye has always been using SoTA techniques. Their EyeQ3 was trained end-to-end before the general public even heard about neural networks. EyeQ3 didn't use NNs but it was trained end-to-end.

It's hard to predict the future but it's easy to look back on history. I just want to know when in the history of humanity has any problem been solved by minimizing the givens? I also want to know when in the history of humanity has a robotics problem been solved by minimizing the givens...

Data being the answer belies a huge (probably purposeful) misunderstanding on behalf of Tesla. AlphaGo was good, it was trained on humans playing Go. AlphaZero is transcendent. The Zero refers to 0 human data used in training. AlphaZero didn't get better than AlphaGo by being fed more data...

One person said it best about FSD: "If you are disappointed by $TSLA EV adoption, wait until you see AV/FSD adoption."

Tesla only needs to achieve a MTBF of 1000 hours. Other companies such as Mobileye or Waymo can waste their time aiming for 10 million hours. Why? Tesla has Neuralink. Even if a Tesla driver gets into an accident, their brain function can easily be restored. This is a long-term competitive...

I predict that on 8/8 Musk will reveal to the world how he plans to synergize FSD with Neuralink. Even if FSD achieves only sub-human reliability, you will be able to regain brain function through Neuralink. Therefore, FSD will reach mass market adoption way faster than Waymo, which doesn't...

10 million hours MTBF ... Where's FSD at, approx 10 seconds or 10 minutes?

Does anyone have a video of a regular person using some form of level 3 automation? Like an EQS owner using L3 in Germany or a BMW 7 series owner using L3 in Germany? Don't want have press videos.

I remember I saw a list of lidar equipped cars in China for MY 2022, and it was like a dozen cars. I remember reading an article about some auto show in the last year in Asia and how 60+ cars had lidar. You're 120% correct. Sensors are getting cheaper and cheaper. There's so many 10 year old...

It certainly helps in taking away in large part the need to classify the object. Didn't Tesla also say they moved away from having to classify what an obstacle is before determining whether avoidance is necessary? At least to me that seems to be the gist of it. Moving away from solely...

Forward lidar should basically guarantee no crashes into sizeable solid obstacles such as stopped cars below a certain speed, and at least a warning above a certain speed.

Thank you for the correction. I'm frankly more curious about the performance of the L2 system rather than the L3 system. I see the L3 system in the Mercedes currently as the cherry on top. It's a very limited system. The L2 system, however, I would hope to be state of the art, with all the...

I don't understand the trashing of the Mercedes system. Sure, the Level 3 part of the system only works under 40 MPH in very particular conditions, but that doesn't automatically mean that outside those conditions, the Mercedes S-Class reverts to a 1975 vehicle with no cruise control and you...

Do you mind linking to Elon's tweet? I scrolled through that Twitter link and can't find any comment from Elon or Tesla.

There's a YouTube video by a diehard Tesla fan showing the FSD consistently brakes for heat mirages.

FMCW lidar in my understanding can return things such as instantaneous radial velocity and so can agile ToF lidar except slower. Perhaps I'm wrong so please correct me. My understanding is that most current lidar systems are ToF based and not necessarily agile.

Yes, the lidar and radar returns need to be processed to identify objects and only then can physical properties be attached to the objects, but, those are pretty much solved problems, unlike the case of vision, where not only do objects need to be identified but techniques for extracting the...

In my view, nearly every FSD beta release notes document highlights how Tesla is throwing an inordinate amount of man-hours and salaries at the problem of getting around the lack of information that an active perception system would grant. Lidar and Radar interrogate the environment unlike...

I think the issue with "basic" map data is that detailed map data is incredibly useful. Think of how many spots where the foliage or overgrown bushes or statues or parked cars block your ability to see enough of the intersection to make an unprotected left turn onto a busy road. Or even a right...

Definitely not unique. Everyone is using neural nets for a large part of the perception layer. Audi in 2017's A8 L3 driving system (that never got publicly enabled) used convolutional NNs. Mercedes' actual production L3 that you can test in Germany at the moment uses CNNs as well...

I'm not understanding the huge optimism surrounding Tesla's vision-heavy approach to solving self driving cars. In what area is Tesla truly ahead of the curve? Even in their bread and butter: battery tech and EVs, Tesla is maybe a few years ahead of other manufacturers at best. You want an...

Sealight isn't a reputable brand with good products. The best upgrade for 9005 halogen is 9011 halogen. This upgrade comes with 0 downsides. HIR 9011 and 9012 bulbs are exactly identical in all dimensions to 9005 and 9006 bulbs, except for two areas, the second of wh

Don't believe everything you read online.

Sorry, couldn't figure out how to edit

No such thing.