Search results

The key to making profit is to shed of loss making business. Let’s see how Alphabet handles Waymo.

Got this error message today. I guess I really pushed FSDs. I need the AI team here now to test and train this out. Maneuver aborted due to system error

The problem with OpenSteet Maps is shown below. See if you can find it.

In all cases, when I am driving, I am doing +20 on curves posted speed limit. Thsoe speed limits are generally for the lowest common denominator ie large trucks with soft suspensions that would understeer dangerously.

Every investment has a projected P&L. How’s that working out?

I also put this on the intake vent to prevent intake of leaves etc. let’s see how that goes.

I have not had the opportunity to test in such a situation where all lanes are empty. Hopefully sometime this week I find a back road and will see how it goes

how is their P&L look like?

I can agree on Baidu with the Chinese government backing but Alphabet is still questionable

The ones who are worried about reporting quarterly profits to the shareholders will not be able to survive this.

From what I saw they are muddying the numbers by having Baidu Taxi drivers drive much of their fleet.

Maybe it is encountering traffic patterns it has not been trained for?

So what is going on? Seems like you know.

This tells me that you have had very bad experiences driving in city at city speeds, but possibly OK on the highways with the old danpers.

There are many possibilities including the possibility ithat the lane change does not help with the next move ie taking an exit. Another possibility I can put forth is there is a vehicle in the other lane that is significantly faster than you are. In this case, it will not switch lanes and...

As do I. The common thought of “Right of way” is so harmful because that makes people limited in their awareness, and to prevent T-bone accidents

Tesla counsel admitted nothing

FSD is not that smart to do a fake out. Rather it is over evaluating the situation and ends up going back rather than making an aggressive and possibly over confident move.

It will not move just because you asked for it. It will evaluate if it is OK to move.

So who has the right of way?

What else you gonna be tuggin' while you are driving?

Glad to know you’re a gifted driver.

Chuck’s UPL is very similar to the UPL I have to negotiate getting out of my neighborhood. 3 lanes going east, 3 going west, (40mph posted speed limit) with a median in the middle. So do you have that UPL?

Took 4 hours to get a Baidu driverless AV. LOL

Keep waiting forever sometimes

Thank you. This sounds sane :)

True....this was just to get back to fundamentals on how NN is built up from here, and the training does contain "data" in their training database.

Agree but I am coming from a legal perspective. The day one of the RT/AV gets into a collision how are they going to prove they are not at fault, and that Tesla RT knew how far the other vehicle/person etc was? Does NN provide that answer? Curious. This is the same situation where S. Ramanujan...

Let’s consider a simple example where you have a dataset of fruits characterized by their weight and texture, and you want to classify new fruits as either 'Apple' or 'Banana'. Training Data: Weight (grams) Texture (0=Smooth, 1=Coarse) Label 150 0 Apple 170 0 Apple 130 1 Banana 180 1...

I am wondering how has Tesla Service reacted to your aftermarket wheels & spacers on your vehicles? Any inputs?

the problem with UPL is to constantly extrapolate the vehicles location that are moving in from the left side, as well as from the right side and find a safe enough time gap to be able to move your vehicle across both sides of the road. Now if any vehicle speeds up while you are performing the...

I would say that they do not see any issue in using or reusing existing tools. Very much like how a psychopath just does not have the ability to understand others pain, and which also makes them the best surgeons. (They both have preternatural calmness under pressure, or apparent indifference...

Been on that route and tons of PB when I was alone within the visible range. So is it Mirages or is it the fact that there is no referential data? Of course cellular signal was also very spotty. I am betting on No reference vehicles as well as spotty cellular GPS causing Anchor Ahoy to be issued

Maybe switch to HERE WeGo! (formerly Nokia Maps) https://www.adci.com/blog/mapbox-or-here-mapping-api https://wego.here.com/

There is a sucker born every minute. That is the reason why Uber does not own any of the vehicle as assets on its books. It would become unsustainable for them.

Actually that is exactly the business model of Uber. Everyday someone will become an Uber driver for earning their bread because it not an impenetrable market like the Taxi was, while another Uber driver is dropping out because it not making them enough to maintain their lives as well as their...

I would tend to agree with you if Tesla had stereoscopic vision for each camera it has. But it does not. Technically without using a complex sensor pixel based focusing system, I see no other way how Tesla would be able to validate distances of objects when it deconstructs and reconstructs a...

You mean this? No wonder India is ahead of the times :D

I agree that it does not do that through a database search but rather the algorithm does that given that every pattern being captured by a Tesla on the road is different yet similar. That is however fuzzy logic and not acceptable in a court of law as there are no specific heuristics that can be...

my city has an app to report a pothole. You can report it by hitting submit button while you are on the pothole, and it will take the geolocation and within the week that pothole is filled up.

From how I understand CNN works, they are decomposing/deconstructing the incoming image into layers of photons, and building a pattern, and recording the human inputs against these patterns. The algorithm(equation) is essentially built to take incoming light from the cameras, feed it as a...

I RP, it is my understanding that the implementation is more like that of an equation that spits out an output based upon the values of the input variables x, y, z, a, b, c etc. This is what makes AI/NN so much faster in response as it is not running through a series of statements that include...

That in itself means they need to start with designated areas for pickup and dropoff, just like a bus stop

Maybe they have tiny people hiding under the hood driving around

Anyone wants to test this road?

What is their coverage look like? Everywhere in Wuhan or just the main few blocks in the city?

Reminds me of a time when I was debugging a german code. Curious me took the comment against it written in german and translated it. It basically said: I dont know why I put this code in here. It does not make any sense but I was told to do so, and I did so. Oh well. Life is fun.

and each of these companies will have to have huge investments for the AV assets as well as the software platform and then fight to survive and ensure that they are not the dry leaves that get shaken off the tree. I am looking forward to it but am very curious as to who really is gojng to be...

The real answer is that the RT will be bare bones. No floor carpet, no cushion seats. Just rubber flooring with gloss painted seats so that nothing sticks.

That is one reason why I have never used Air BnB.