Search results

I've been letting FSD v12.3.3 (and 12.3) drive me nearly everywhere for the last few weeks, sitting at 99 safety score with only late night driving dinging me.

I was under the impression that any miles driven on AP/FSD don't count against your safety score. Is that no longer the case? In any case, if you feel it about to slam on brakes for no reason, you can simply feather the accelerator to cruise throught the yellow light.

For some insanely narrow definition of useless, sure. But I use it 99% of the time every day and so, to me, it's far from useless, even in this state.

Worth noting that in some ways, we have already surpassed Data. Recall, in early seasons Data didn't understand humor and didn't have emotions like empathy.

https://www.nature.com/articles/d41586-023-01883-4

The right side of the road is just a suggestion

FYI, googling moravec’s paradox has this as the first hit: “By the 2020s, in accordance to Moore's law, computers were hundreds of millions of times faster than in the 1970s, and the additional computer power was finally sufficient to begin to handle perception and sensory skills, as Moravec had...

I see your LeCun and raise you a Karpathy:

Many in the AI industry think AGI is only a few years away so it might not matter. LeCun is in the minority here.

Subie being outSubied

Citation needed. Exponential growth is hard af to predict since you have no idea where you are on the S curve.

Do we know if each car model (3, Y, S, X) has its own NN model associated with it? Or is there a general HW3 model that works across all 4 Models?

Devin uses ChatGPT:

Seems less than 16 years away to me:

ChatGPT very much lives up to its hype.

ChatGPT moment very clearly means “goes viral in the way ChatGPT did in November 2022”, when, let’s see, it replaced exactly 0 humans.

Can’t tell if serious. This post is very unSubie-like. Alan nod twice is you’re being held captive by ChatGPT.

Uncharitable interpretation of “ChatGPT moment.” Clearly what is meant by this phrase is a huge shock to society about what is possible and now the near-future could look radically different than the present. It isn’t about replacing humans, it’s about waking them up.

In short, there is very little logic. It's "random" with some subset of cars being favored by the developers depending on what they're working on. For example, back in the v12.0, 12.1 and 12.2 timeframe, they were only pushing to first OG testers/social media influencers and then random VINs...

If you use the old speed selection, does that force it into v11 mode? Both seem v12 to me but hard to say in very limited testing.

12.3 now on both of our HW3 3s, in Baltimore, MD. Testing in Baltimore City for 15 minutes or so went well!

As a user of FSDb in both 2022 and 2024, I can say that it's improved, but not by that much. Moreover, as someone who drives the same routes on a daily basis, in nearly every drive, it makes the same mistakes over and over again, without fail. In the article, the driver tells the passenger "it...

We may never know if the car in question was using FSDb at the time of the crash (though Elon's tweet is highly suggestive that it was not), but what we can for sure do is take current FSDb and go drive the same road and see how it performs. Who here lives close enough to the road in question...

https://www.washingtonpost.com/technology/interactive/2024/tesla-full-self-driving-fatal-crash WaPo reporting on an FSD-involved fatality of a Tesla employee. Did we already know about this or is this breaking news?

It's running on both.

That's a theory. Any actual evidence to back this up? (This is what I'm getting at...)

Personally, I do not see much difference in nagging in the latest FSDb builds compared to previous. You just need to hold the wheel right and you'll never/hardly ever get a nag.

Why not Chuck Cook? He's arguably the most grounded FSD influencer.

Right, the question is, why? Why only Whole Mars?

Where our Chuckie Cook vidz at?

video please

I think the question is can a model of this sort assist with tasks required by AVs and the answers from this paper make it clear: absolutely they can. GPT4V wasn't even trained to do this thing. You can imagine a smaller model built for much more specific purpose and trained on only the most...

Full paper here: https://arxiv.org/pdf/2311.05332.pdf

@Bladerskb how’s Xpeng doing, two years on from this thread?

OP, FSD or FSDbeta? They are different...

Stop sign behavior is variable. Sometimes it behaves relatively humanlike and other times it's too cautious.

Perhaps I'm not being clear. Sometimes, you see a sign and it tells the car what it can do. Sometimes you see a sign and it tells the car what it can't do. Sometimes you don't see see a sign and, depending on where you are in the world, you are allowed to do something or it is illegal to do...

Right, and that's my point: most of the time, a sign will tell you what you can't do. But sometimes it's the absence of a sign that tells you what you can't do. How does the model figure out which is which?

Opposite reaction: extremely f'ing believable.

Thought experiment for current end-to-end AI systems: Imagine a world in which in 99.999% of the world, you may turn right on red UNLESS there is a sign that says "No right turn on red." In %0.001 of the world, it is illegal to turn right on red unless there is a sign that explicity allows you...

It's interesting right because DeepMind created AlphaGo, giving it knowledge of many human games, and AlphaGo ended up able to defeat the world champion. Since then AlphaZero throws out the human games altogether and simply learns from itself.

OP, any thoughts? Seems pretty good to me for alpha:

Yeah if 10x better than 11.4 isn’t “better” to you then yes, this won’t be “better.” I realize we do need 1000000x better than 11.4 to get to robotaxies but for my commute, 10x better than 11.4 is amazing (as I already use 11.4 for every single commute). We then turn to, what is the rate they...

Based on the recap right above this that I posted, I suspect this will age poorly. Car is more humanlike than ever in that video.

Can someone transcribe the Qs and As?