[jlmorton]

That's exactly what Elon has said. He's said that 99.99% of all vehicle miles are useless from a training perspective.

https://www.teslarati.com/fsd-distance-driven-training-musk/

[croes]

That's not the same. Elon thinks if he gets the right training data he gets rid of the dangerous 1% of errors.

But that is not the case if it's a general problem of the used AI.

[forgot-im-old]

Right, getting more corner cases training data won't solve an architecture problem. AI in general quickly impresses when it's mostly right but improving from there is the challenge.

[throwaway7ahgb]

What are you using for "AI"? AI is a buzzword, unless you know specifically how they are using it, you can't make this claim.

Many marketing teams are just using AI when it is really ML doing the work, or it could be both.

[what-the-grump]

And yet on a very simple drive I have to intervene 4-6 times over a distance of 8 miles. How is this not useful? It would have been easier to ask people to record how to drive roads by now and use video game track logic where you race a ghost by now…

The only time fsd works ‘ok’, single lane roads with 90 degree stop signs / turns.

I don’t believe that the current hardware can handle what is needed to have passable FSD for an average consumer.

[georgeg23]

So isn't that a deep problem to his FSD architecture?

[acchow]

No. For the easy 99.999% of driving they keep very little of the training data.

Basically you want to minimize manual interventions (aka disengagements). When the driver intervenes, they keep a few seconds before (30 seconds?) and after that intervention and add that to the training data.

So their training data is basically just the exceptional cases.

They need to just make sure they don’t overfit so that the learned model actually does have some “understanding” of why decisions are made and can generalize.