Andrej Karpathy

The cost is high, and you're not potentially seeing it if you're just a computer vision engineer, and I'm just trying to improve my network, and is it more useful or less useful?

How useful is it?

And the thing is, once you consider the full cost of a sensor, it actually is potentially a liability, and you need to be really sure that it's giving you extremely useful information.

In this case, we looked at using it or not using it, and the delta was not massive, and so it's not useful.

And these sensors, you know, they can change over time.

For example, you can have one type of, say, radar.

You can have other type of radar.

They change over time.

Now suddenly you need to worry about it.

Now suddenly you have a column in your SQLite telling you, oh, what sensor type was it?

And they all have different distributions.

And then they contribute noise and entropy into everything.

And they bloat stuff.

And also organizationally, it's been really fascinating to me that it can be very distracting.

If all you want to get to work is vision, all the resources are on it, and you're building out a data engine, and you're actually making forward progress because that is the sensor with the most bandwidth, the most constraints in the world, and you're investing fully into that, and you can make that extremely good.

You have only a finite amount of spend of focus across different facets of the system.

Yeah, I think this debate is always slightly confusing to me because it seems like the actual debate should be about do you have the fleet or not?

That's the really important thing about whether you can achieve a really good functioning of an AI system at this scale.

So data collection systems.

Yeah, do you have a fleet or not is significantly more important whether you have LiDAR or not.