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

Scenarios in which Tesla FSD Beta 9.0 fails

twitter.com

Post reply on HN
Print view View original

171–180 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#171

Post by throwaway-8c93 »

visarga wrote: post #85
Syonyk wrote: post #48

Earlier quoted context omitted.

Aviation and space are a very, very different problem space from surface street navigation, because they rely, almost entirely, on "nothing else being there." We've had good automation in aviation for decades. It doesn't handle anything else in the way very well at all, and while there's some traffic conflict avoidance stuff, it's a violent "Oh crap!" style response, nothing you actually want to get anywhere close to…

> There's nothing it really has to look at and understand that it can't easily get from some basic sensor data - speed, attitude, location, etc. Self landing rockets are simple, it's not rocket science, duh! Everyone and my grandma has one.

Propulsive landing has been achieved routinely and with perfect precision since the 60s - Apollo's lunar modules, Lunar surveyor, Lunokhod rovers.

The question has never been about the feasibility of landing the booster stages - what has been questioned is whether it's worth doing. The fuel used up during landing is fuel that cannot propel the payload. The landing might fail. The effects of thermal and material fatigue are not well understood. The transportation, refurbishing and QA are unlikely to be cheap anyway.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#172

Post by AtlasBarfed »

Syonyk wrote: post #45
stsmwg wrote: post #29

One of the questions I've repeatedly had regarding FSD (and Tesla's approach in particular) is the notion of memory. While a lot of these scenarios are disturbing, I've seen people wavering on lanes, exits and attempting to turn the wrong way onto one-way streets. People have memory, however. If we go through the same confusing intersection a few times, we'll learn how to deal with that specific intersection. It seem…

This has been a common assertion about Tesla's "leadership" in the field - that they can learn from all the cars, push updates, and obviously not have to experience the same issue repeatedly. It's far from clear, in practice, if they're actually doing this. If they have, it would have to be fairly recent, because the list of "Oh, yeah, Autopilot always screws up at this highway split..." is more or less endless. GM's…

RE: determining what humans did was right to take over

It's a QA department. If there is a failure hot spot, then take a bunch of known "good" QA drivers through that area. Assign strong weight to their performance/route/etc.

It's interesting reading through all this, I can see a review procedure checklist:

- show me how you take hotspot information into account

- show me how your QA department helps direct the software

- show me how your software handles the following known scenarios (kids, deer, trains, deer weather)

- show me how you communicate uncertainty and requests for help from the driver

- show me if there is plans for a central monitoring/manual takeover service

- show me how it handles construction

Also, construction absolutely needs to evolve convergently with self driving. Cones are... ok, but some of those people leaning on shovels need to update systems with information on what is being worked on and what is cordoned off.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#173

Post by cptskippy »

manmal wrote: post #159

Is FSD still operating on a frame-by-frame basis? I remember it was discussed on Autonomy day that the ideal implementation would operate on video feeds, and not just the last frame, to improve accuracy. When you look at the dashboard visualizations of the cars‘ surroundings, the model that is built up looks quirky and inconsistent. Other cars flicker into view for one frame and disappear again; lane markings come an…

I would think the flickering objects in the UI is a result of objects hovering around the confidence threshold of the model. But... I have a Model 3 and the flickering happens when stationary and nothing around you is moving.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#174

Post by cs702 »

richwater wrote: post #129
cs702 wrote: post #120

Many of the comments here seem a bit... unfair to me, considering that these clips were handpicked. I watched (and fast-forwarded) through a few of the original, full-length videos from which these clips were taken. The full-length videos show long drives (in some cases, hours long) almost entirely without human intervention, under conditions explicitly meant to be difficult for self-driving vehicles. One thing I rea…

It literally doesn't matter how well it does in 90% of situations when the other 10% can injure or kill people in relatively basic scenarios like the Tweets presented. I mean the car almost ran into a concrete pillar like it wasn't even there. > For BETA software, FSD 9 is doing remarkably well If this was a React website, that'd be great. But it's a production $40,000 multi ton automobile.

> ...doesn't matter how well it does in 90% of situations...

Based on the full-length videos, I'd say it's more like 99.9% or even 99.99% for FSD 9.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#175

Post by llbeansandrice »

dekhn wrote: post #55
bsagdiyev wrote: post #51

Why are there so many comments from seemingly different posters all saying the same thing on this, "I don't understand why humans are allowed to drive cars"? It feels kinda... culty? Or too similar to be a coincidence. It honestly probably is but these Tesla posts always bring out those types and it confuses me. Humans kill humans, do we want machines to start doing it on the road automatically now too?

I think the idea is, if humans were held to the standards machines are, we wouldn't let them drive. If you offered me a car that drove itself, and statistically, it killed people at the same rate as humans, but let me not have to drive, I'd take that. Nobody everybody agrees.

> if humans were held to the standards machines are, we wouldn't let them drive.

That's not how it even works though. When people crash or drive drunk there is a system to hand out consequences. What do you do when a Tesla drives into a monorail pole and causes millions in damage if the structural integrity is compromised?

>statistically, it killed people at the same rate as humans

You can't tell me a car that's at best an average not-murderer is a good sell.

There are also so many ways to self-determine your risk while driving or traveling in general. A clear example is seat belts. Less than 10% of people in the US don't wear seat belts but a full 47% of the people that died in car accidents were not wearing one. [1]

1 - https://www.nhtsa.gov/risky-driving/seat-belts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#176

Post by wedn3sday »

throwaway0a5e wrote: post #41
wedn3sday wrote: post #28

I watched a human driver in a BMW weave at 90 mph through traffic yesterday, swerving back and forth between lanes inches from other peoples cars. If Tesla can make a car that's even 1% less dangerous than human drivers, that could be thousands of deaths avoided every year. Humans should not be allowed to drive cars on public streets.

The fact that a presumably average or not too far from average human can "weave at 90 mph through traffic yesterday, swerving back and forth between lanes inches from other peoples cars" should tell you how wide of a gulf there is between human operators and current FSD tech, which will dodge road debris only if it looks like a car, person, cyclist or traffic cone.

Yes, Im "pearl clutching" because some ahole decided to put hundreds of peoples lives at risk so he (and its always a he) could have a little thrill. There is a wide gulf now between human skill and robo-driver skill, just as 50 years ago it was much faster to call someone then send them a message in the mail. Now we have email, and in the future we will have (actual, real) full self driving.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#177

Post by camjohnson26 »

bob33212 wrote: post #146
richwater wrote: post #129

Earlier quoted context omitted.

It literally doesn't matter how well it does in 90% of situations when the other 10% can injure or kill people in relatively basic scenarios like the Tweets presented. I mean the car almost ran into a concrete pillar like it wasn't even there. > For BETA software, FSD 9 is doing remarkably well If this was a React website, that'd be great. But it's a production $40,000 multi ton automobile.

People will die today because a driver was drunk/distracted/suicidal/rode raged or had a medical problem. Are you OK with that or do you think we should attempt to fix that with software? If you do think you should attempt to fix that, do you understand that software engineering is a iterative process? It gets safer overtime.

Eliminating drinking would get rid of a huge number of automobile accidents. Sober humans are incredible drivers and we don’t have self driving cars that are better than even poor humans, as long as they aren’t impaired.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#178

Post by AtlasBarfed »

croes wrote: post #4

I doubt that autonomous driving will work in the next couple of years without infrastructure adjustments. We built roads for cars to replace horses, we will need to built roads for autonmous cars to replace human driven cars.

The infrastructure convergence should concentrate on highways, where the highest speeds, most use, but conversely the least complicated algorithms are needed.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#179

Post by camjohnson26 »

foepys wrote: post #165
bob33212 wrote: post #146

Earlier quoted context omitted.

People will die today because a driver was drunk/distracted/suicidal/rode raged or had a medical problem. Are you OK with that or do you think we should attempt to fix that with software? If you do think you should attempt to fix that, do you understand that software engineering is a iterative process? It gets safer overtime.

> People will die today because a driver was drunk/distracted/suicidal/rode raged or had a medical problem. That's a straw man argument. Mandatory breathalyzer tests before every engine start and yearly medical and psychological check-ups would solve a lot of these problems as well. > It gets safer overtime. There is no evidence of this happening yet. It's still trying to drive people into concrete pillars. Remember…

Local maximums exist. If ML models were guaranteed to improve over time we would have no more problems to solve.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#180

Post by camjohnson26 »

cameldrv wrote: post #153
cs702 wrote: post #120

Many of the comments here seem a bit... unfair to me, considering that these clips were handpicked. I watched (and fast-forwarded) through a few of the original, full-length videos from which these clips were taken. The full-length videos show long drives (in some cases, hours long) almost entirely without human intervention, under conditions explicitly meant to be difficult for self-driving vehicles. One thing I rea…

Supposedly there are a "few thousand" FSD beta testers, and only a small fraction of them are videoing their drives and uploading them to YouTube. Beta 9 has existed for 2 days. This puts a pretty high lower bound on the serious error rate.

The consensus is that there far fewer than a few thousand
Post reply on HN