The bitter lesson is finally coming for the self-driving cars. The vision stack, 3D maps, lane selection grammar, occupancy networks, it’s maybe all about to give way to a single GPT looking at camera feeds and predicting the next steering wheel adjustment.
It’s mostly a latency problem at this point. The models are too big to run locally, but given that open-weight models like Qwen already exist, an open-weight, low latency equivalent to Astra can’t be too far out.
I'm not sure how you take that from the original article. My 4 year old would drive that course in an automatic car, if only he could reach the pedals. Heck, he's done harder things at Lego land.
I wouldn't let him loose on the road though.
I think, at the very least, the guardrails would have to deterministic, ideally with super human senses, for people to accept self driving cars on the road.
Nope, no "deterministic guardrails" for you. The domain is simply far too broad and unstructured to allow for that.
Unless you mean "a typical AI with all the computation constrained sufficiently to always unfold the same exact way, given the same input". In practice, that just kicks the can to "given the same input" street.
The noise in the system is going to come from the input plane. Which is, I remind you, facing the real world. It's full of noise.
Almost certainly, there are 4 year olds who ride small motorbikes etc. I think the main problem is that they can't really be held accountable if they have an accident.
16 year olds are bad enough on the road: <a href="https://www.hallandalelaw.com/wp-content/uploads/2013/07/IIHS.CHART_.CRASHESBYAGEGROUP.png" rel="nofollow">https://www.hallandalelaw.com/wp-content/uploads/2013/07/IIH...
valine · · focus · HN ↗
It’s mostly a latency problem at this point. The models are too big to run locally, but given that open-weight models like Qwen already exist, an open-weight, low latency equivalent to Astra can’t be too far out.
VBprogrammer · · focus · HN ↗
I wouldn't let him loose on the road though.
I think, at the very least, the guardrails would have to deterministic, ideally with super human senses, for people to accept self driving cars on the road.
ACCount39 · · focus · HN ↗
Unless you mean "a typical AI with all the computation constrained sufficiently to always unfold the same exact way, given the same input". In practice, that just kicks the can to "given the same input" street.
The noise in the system is going to come from the input plane. Which is, I remind you, facing the real world. It's full of noise.
sealWithIt · · focus · HN ↗
[dead]
chaos_emergent · · focus · HN ↗
DennisP · · focus · HN ↗
[dead]
Davidzheng · · focus · HN ↗
VBprogrammer · · focus · HN ↗
stickfigure · · focus · HN ↗
tim333 · · focus · HN ↗
pishpash · · focus · HN ↗
an0malous · · focus · HN ↗
aerhardt · · focus · HN ↗
What's your ARR, anyway?