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.
Tesla's already solved this - their vision model does this phenomenally well.
And they've demonstrated adding a sidecar LLM to it as well, mostly for these kinds of "read these 3 street signs, what should i do next?" sort of situations.
Anecdotes. Only accident rate per mile driven (compared to human drivers' rate) is a relevant comparison. I don't think that any self-driving system will ever be absolutely perfect (all such complex non-linear systems are to some degree probabilistic and chaotic), but as long as the accident rate is lower than the human accident rate, I would consider it solved.
> Only accident rate per mile driven (compared to human drivers' rate) is a relevant comparison
This is such an insane take I see all the time from self-driving boosters
If a self driving car glitches out and crashes in some edge case pathological scenario we don't just accept that as totally fine because its hidden under big statistics
The reason why a crash happened does matter, its not just about aggregate statistics
As a thought experiment if I have a perfect self driving system but I add some code that purposefully crashes 1 in 10 million rides are you ok riding in it since the aggregate statistics look good?
> As a thought experiment if I have a perfect self driving system but I add some code that purposefully crashes 1 in 10 million rides are you ok riding in it since the aggregate statistics look good?
Do I know about the purposefully added harmful code? If yes, I would demand you remove it, because why not. If I don't know about the code, I would be OK with it, since it's clearly still more safe than the alternative and apparently cannot be made even better.
You seem to be neglecting the important part of that scenario where you're other option you have to compare it to is a human driver that will randomly get it a crash at some higher rate.
You're making it sound like the obvious answer is the irrational one.
It's Lego mindstorm logic level to drive a car on the motorway, so per mile is an absolutely insanely bad metric in general.
Per mile inside cities or other difficult scenarios are what may get close to an actually meaningful metric. That's why Tesla is very misleading and waymo is much more legit.
Cute, but no. Can't compare a self-driving system that's only willing to work in a subset of conditions humans drive in, to humans driving in all those conditions.
You added "totally" - as others have said, I don't know if anyone will claim a perfect system with no fatalities, enough stats show that it is already much safer than human drivers.
And the true third party validation is that insurance companies are starting to offer lower premiums the more you use FSD. So their risk models are showing enough improvement that they're putting their money where their mouths are.
The idea that Tesla's FSD is not ready for the mainstream is quite outdated, given that tons of Tesla owners are already using it daily, not just your early adopter types.
Note that the article has no info on whether it's FSD or Autopilot and whether they contributed to the fatal crashes. "Verified engaged" means ADAS was active at some point in the interval from T-30s to the end of the accident. The total number of collisions is not normalized by the miles driven.
It also has no info on what hardware+software version was in use. The older cars are significantly less capable but there are far more of them on the road.
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.
atonse · · focus · HN ↗
And they've demonstrated adding a sidecar LLM to it as well, mostly for these kinds of "read these 3 street signs, what should i do next?" sort of situations.
overgard · · focus · HN ↗
Obscurity4340 · · focus · HN ↗
Marha01 · · focus · HN ↗
ex-aws-dude · · focus · HN ↗
This is such an insane take I see all the time from self-driving boosters
If a self driving car glitches out and crashes in some edge case pathological scenario we don't just accept that as totally fine because its hidden under big statistics
The reason why a crash happened does matter, its not just about aggregate statistics
As a thought experiment if I have a perfect self driving system but I add some code that purposefully crashes 1 in 10 million rides are you ok riding in it since the aggregate statistics look good?
Marha01 · · focus · HN ↗
Do I know about the purposefully added harmful code? If yes, I would demand you remove it, because why not. If I don't know about the code, I would be OK with it, since it's clearly still more safe than the alternative and apparently cannot be made even better.
parineum · · focus · HN ↗
You're making it sound like the obvious answer is the irrational one.
gf000 · · focus · HN ↗
Per mile inside cities or other difficult scenarios are what may get close to an actually meaningful metric. That's why Tesla is very misleading and waymo is much more legit.
Mawr · · focus · HN ↗
atonse · · focus · HN ↗
And the true third party validation is that insurance companies are starting to offer lower premiums the more you use FSD. So their risk models are showing enough improvement that they're putting their money where their mouths are.
The idea that Tesla's FSD is not ready for the mainstream is quite outdated, given that tons of Tesla owners are already using it daily, not just your early adopter types.
red75prime · · focus · HN ↗
Rohansi · · focus · HN ↗