Search results

It stopped right after the video, after I turned climate on and then back off again. Also it's in the 30s where I'm at right now.

I own an MY and am currently out of state, renting a 2022 MS off turo. After supercharging tonight to 70%, when I arrived at where I'm staying, I noticed a super weird crackling noise coming from inside the frunk. https://streamable.com/cw1xoy It almost sounds like it could be electrical. But...

I have a similar train of thought. I'm very impressed by what Tesla has with vision only. It's a low resolution approximation of what you'd get with LIDAR, but it comes with the added benefits of not having to do sensor fusion, and it comes out of embarrassingly cheap consumer hardware. It's not...

I draw the opposite conclusion. Imagine how much confidence that Waymo - an extremely cautious and conservative company (perhaps too much so) - must have to let their cars go out and about with real passengers and without a backup driver. Now look at Tesla. They won't even let you be a _backup...

Agreed, which is why it took until self driving cars didn't need special infrastructure to operate for them to become a thing. The fact that they run on normal roads is exactly what will drive their adoption. They just wouldn't work any other way.

Except they didn't say "we think it has ..." they said "it does have ...". And they didn't say "contingent on validation" they said "pending validation". Very clearly negating your theory.

Tesla has not delivered even 1X of what they promised with FSD. Even among the few who have the feature, it provides _negative_ value since it doesn't make the task of driving easier. Meanwhile Waymo has operational robo-taxies, and many other companies are racking up thousands and thousands of...

People's understanding about things are shaped bit by bit from all of the information they may come across. Lies spread and gain traction the more frequently that they are repeated. In the case of Teslas, lies from an _owner_ carry more weight. Why do you want to be part of the problem?

This statement is false and dangerous. No Tesla vehicles ship with any L4 features today, and no filings with the government have been made from Tesla to indicate that they are even actively developing any > L2 features. L4 has a strict definition and NOA does not meet it. Your post is...

I saw a Silicon Valley Tesla Club video where the car avoided a tree that was randomly in the middle of a road, and also a Dirty Tesla video where it finally avoided a Road Closed sign. In both cases the response was super jerky and it barely made it... but the car clearly did react to...

So there are three promises: 1. Elon's different verbal promises 2. purchase page circa 2017 After what time has passed would you consider an FSD class action lawsuit? 3. purchase page today (doesn't seem to have much specificity, just "autosteer on city streets") For 1, Elon clearly promises...

The way I take your comment to mean is that if we can build a computer that behaves like a brain, it could be harnessed to solve the same problems humans can, except it will not ever make mistakes and be infinitely faster in decision making. This is a very common, likely false, line of...

Yeah. L4 systems will improve, but the ones that become commercially viable in the short term, IMO, rely on things that do not apply to consumer vehicles: namely, remote assistance, and purpose built hardware. I think FSD could be a good L3 system one day. The only concern I have is the...

I'm personally not as sure of this. I feel like there are too many places where the car can get stuck, and most of the places that a car can get stuck aren't known or trainable for. Getting stuck (either locally stuck, or in a navigation loop stuck) as a robo-taxi passenger isn't acceptable. I...

What am I wrong about? That Tesla's cannot become driverless without some human somewhere capable of giving it instructions of some kind when it encounters an unexpected scenario? Or that high definition maps are not that difficult to produce and maintain, are worth the effort, and are...

I'm not sure you understand the real difference between a driverless robo-taxi and an ADAS. Admittedly, Tesla has done a great job at obfuscating the issue. A driverless vehicle cannot operate on roads where the road signs are only "fairly consistent" without some human in the pipeline to make...

"Proved to be inaccurate" is certainly one choice of words (I'm far from a Tesla hater but I found that euphemism to be funny :p). Back on topic, I don't agree with Lucid's CEO's assessment. If we're talking about a system that requires no human involvement - not even remote operators - he has...

Regardless of maps or no maps, you're never finished. New signs and road semantics will always be introduced. One off signs are a thing. Because AGI isn't yet possible, no car is going to automatically understand new signs or markings until they're programmed to do so. Tesla ignores this...

It does look like it got kinda stuck there. Do you have the full video for this clip? I'm not doubting your point BTW, I'm just curious about this clip in particular.

It's interesting that you mentioned bar coded medicine administration. This eventually helped reduced errors, but introduced entirely new classes of errors where nurses would bypass the system by wearing duplicate barcodes on their person instead of scanning the ones on the patient. Point being...

Hm, maybe he's changed his attitude, but he hasn't come across like that in the few months I've been watching his videos. In fact he clearly states that the beta rollout is a numbers game, and that he's not anybody special. The basic argument (with arbitrary numbers) is that having 1,000 users...

Elon has literally said the car will avoid obsticals that it can't recognize; he has repeatedly talked about the car being able to stop even if a UFO crash lands on a highway. We also know that the car has such a capability, with the voxel outputs that have been demoed before, and the monorail...

I don't think a lot of people understand how unfinished FSD beta is though. They may be expecting stability along the lines of other kinds of betas... Which they are simply not going to get (unless 10.2 is a massive improvement).

L5 is wishful thinking I agree; but do you really not think that geofenced L4 robo-taxies that don't require remote operators, or door to door L2 ADAS with minimal disengagements, is feasible within the next 6-12 months? I look at Waymo, Zoox, Tesla, and IMO, I personally believe all of the...

What's the bandwidth of the bus that the cameras are all attached to? Is it known that it's capable of handling the additional data without rewiring?

Tesla would be insane to give FSD to a very high percentage of people right off the bat. _I'll_ be disappointed if they don't go very, very, slowly, with plenty of "bake time" between the next set of people added to the pool.

Waymo and Tesla are building two different products, and for one to succeed it doesn't mean the other needs to fail. I don't understand why people are so desperate that their favorite company "wins" or that their least favorite company "loses". We all win with this technology moving forward.

It's beta until Tesla says it isn't. If it can perform highways with few to no interventions, yet still requires interventions on city streets, my point that it is still useful, yet still firmly in "beta" territory. I thought my post was clear on this. My entire post is the observation that...

Just don't use NOA. I personally am not a fan. I do like the feature where it will execute a lane merge when I tell it to. Otherwise, I treat AP as a highly advanced lane keep assist + adaptive cruise control. I don't grant it any more intelligence than that, and am therefore not disappointed...

That whole video was pretty embarrassing. I'm not sure if I've ever seen a tester let it fail so badly in a populated area. I doubt it would make the same mistakes had there been no traffic or pedestrians around, so I'm not against testing such scenarios*... but he let the car cross the line too...

Wasn't it supposed to come out at midnight though? A source on Twitter earlier today said it was on track. Did it actually get delayed again?

Out of curiosity, what do you think it is about the hardware that will prevent FSD from operating at 2x human safety on HW3, or, at the very least, HW4? There are known issues with camera positioning, but it seems like those should be corrected by the time HW4 comes out, now that Tesla has much...

The only people who can afford these cars as they are priced today should know better.

Yeah, it's been said that autosteer wasn't enabled. But was TACC? I think if it was, it becomes an autopilot issue, especially since it's easy to confuse the two. On my very first times driving my MY and learning autopilot, autosteer disengaged, but TACC remained active. As somebody who never...

I have a radar-enabled Model Y (108xxx VIN) on 2021.12.25.11 with about 3,000 miles on it, and have only experienced a couple instances of unexplained breaking, after thousands of miles on I5 with autopilot. It's really disappointing to hear that the vison only cars are worse.

I have the benefit of only starting to pay attention recently. I admit that the experience of those who have been watching since day one is filled with a lot more disappointment. I'm not sure what I can say to bridge those two experiences, other than to simply point out that they are different.

I'm not sure I follow. Moving from single frame training to training on video shouldn't require different data? Just instead of sending single frames for training, they send in the entire video clips. I guess I'm assuming that they've been collecting video clip data from the fleet this whole...

That's interesting. I'm not surprised they throw out most of their data. Also they have a limited amount of bandwidth to label it, even with automation. It's still important to collect lots of video of the same scenarios, not just for training, but also validation... but yeah, at some point...

The cool thing about Tesla's data advantage is that it doesn't disappear when they retrain their NNs. Their data pipeline has undergone massive improvements over the last 4 years. Every time they modify the architecture, they "retrain" using that same data they've collected, plus whatever new...

I get the joke, but they reached the limits of what their previous stack could do, and had to take a few steps back. I'm happy to keep using the older implementation until they demonstrate the newer implementation is actually better.

> The fact that TACC is one of the worst TACC I've driven is absolutely criminal. Is it? I haven't used level 2 features of any other car manufacturer, but TACC/autosteer has been fantastic. The only feature it's missing is more robust driver attentiveness monitoring, allowing you to take the...

> C++ > safe I know that's not what you meant by "safe" but still. Why is new software still being written in C++?

Elon stated unequivocally, multiple times, that the cars being manufactured had all of the hardware required for L5 autonomous driving. Also anything he says about robo-taxies implies at least L4. The name "FSD" doesn't matter since he spelled out specific functionality that the car would be...

I've never had an issue with the name autopilot. I'm not a pilot, but I have a basic understanding of what autopilot in avionics does, and it seems the systems are comparable. But this thread is about FSD. And I hate to admit it but I think that it could very well have a legal standing. Elon's...

I think not having a steering wheel is a liiiiitle more ridiculous than not having a HUD. Everything from that book is suspect in my mind TBH. Especially after the Tim Cook thing.

Yeah, that first mistake was bad. At residental speeds (25mph) it wasn't as bad as it could have been but it still wasn't great. Like the guy in the video said - the auto corrective behavior was nice to see - but ultimately the car should not have tried to or have been allowed to make that...

The flickering in and out could be many things, maybe the NN not detecting the object as it changes angles or comes out of view from one camera and into view of another. Computer vision tends to be very flakey like that. For what it's worth; human vision is probably "flakey" in the same way...

Poor prediction of other cars seems to be the bottleneck. Elon has also aknowleged prediction as being a big focus for their next minor release, so maybe 9.2 will see some improvement in this specific scenario.

Oof. I thought he was getting better about that recently :/ seems old habits die hard.

Right, but if the FSD system aborts the left turn and forces the navigation to re-route, if it could remove that left turn from consideration during the re-route, presumably the car wouldn't get stuck, since it would be trying a different path every time