HN

Need help?
<- Back
GPT-6 Astra has gained the ability to drive a car

GPT-6 Astra has gained the ability to drive a car

plurby

Comments (161)

  • jyoung8607
    I'm not an expert in the LLM space, but I'm an external contributor to comma.ai's openpilot project and I'm and quite familiar with how its controls work, so I looked from that perspective. There's two questions here:1) Could a cloud-delivered LLM figure out how to drive this route, based on those input data and given access to those output actuators? Looks like yes. Sure.2) Could this work in the real world? Absolutely not. Three reasons: latency, latency, and latency.openpilot's driving model updates the target curvature and acceleration at 20Hz. Every millisecond of the round trip time through every piece of its entirely-local driving stack is well-understood, extremely consistent, and tightly optimized. It has to be, otherwise you can't react to even minor bumps or wind gusts, much less rapidly-developing traffic situations.Adding even a single speed of light RTT to a cloud service is meaningfully bad, and you'll need a whole lot more to encode and upload camera imagery to even start the time-to-LLM-response clock, and then send the response back down. By then the world around the car has moved on.There's a reason Tesla and every other self-driving manufacturer need the compute hardware in the car.
  • valine
    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.
  • famouswaffles
    What did they do to Astra so cracked at vision (and computer use). That ARC 3 score turned out to be no joke/fluke. That huge gap between Astra and Fable (in this case) is basically every hard vison/spatial benchmark i've seen including non-benchmarks like playing games (Portal, Factorio, RimWorld).SpatialBench - https://x.com/spicey_lemonade/status/2096365630190698516ZeroBench - https://zerobench.github.io/Robot Arms - https://openai.robocurve.org/gpt-6-astra/
  • prometheus1992
    Wow! but WHY is this a benchmark?? for comparison tesla's model is approximately 10-15B parameter model (estimating from maxxing the hardware that comes with the car at 16gb ram).
  • syntaxing
    Surprised they didn’t try Qwen’s recently open sourced driving model https://huggingface.co/Qwen/Qwen-Drive-1.0-4B
  • sys32768
    Has anyone else noticed human drivers becoming more aggressive and causing more accidents than ever?I thought it was because my smaller town was overrun after COVID by transplants, but I'm hearing similar complaints from other places I was considering relocating to.Perhaps the solution will be robocars where, if there's a potential road rage scenario, the passengers can duke it out in a VR headset session.
  • amluto
    I’m morbidly curious whether the (supposedly) superior compaction support in recent GPT models with an appropriate harness has anything to do with this. A conventional LLM with conventional attention is, of course, wildly unsuitable to continuous tasks like driving, but maybe as the technology advances it will improve in its ability to sort-of work.
  • 1970-01-01
    Looking forward to the juggling bananas benchmark. If Claude can only manage 5 and Astra does 6, clearly they have a better model.
  • soumyadeb
    This also explains why Astra is so good at video generation. I have an Astra+Higgsfield setup. I could point it to a Github repo and ask it to generate a product walkthrough and it did a very good job by generating fake screens (e.g. with data filled in) from real ones - which wasn't possible in earlier models
  • 4b11b4
    Nah
  • nashashmi
    I wonder if the companies would be willing to bet entirely on AI driven innovation if liability for misalignment was put squarely on companies, individuals, compute vendors, and LLM vendors. I don’t think they would opt for it, especially if an alternative option to use human-programmed tech was already available.There is something to be said about emphasizing on liability as a way to freeze or solidify AI Development. Right now it is too unfettered leading to predictions of AI dooms.
  • overgard
    I appreciate this on a nerd level, but this just seems like a bad way to use an LLM. There are better artificial intelligence techniques for solving spatial problems.
  • vb-8448
    Wow .. fascinating but I guess something like JEV is more appropriate here.
  • marginalx
    Could this work to drive robots in a confined space without humans, and time isn't a huge factor, where full automation with scale can still be economical, like in a lights out environment?
  • pietz
    Apparently I have a new favorite benchmark. Honestly, this is cool.
  • josefresco
    Looks like the "most successful" path drove over empty parking spaces and came close to two curbs?
  • Mooty
    How do they even test this on a model ? I mean it's a multimodal i get that but response time are too big or am i missing something ?
  • zezcko
    I think the most interesting part of this is that Astra initially refused to drive because it realised it was driving a real car and would only obey when the MCP was renamed to DrivingBench Sandbox. This is both an interesting detection by the LLM but also for me an interesting dynamic concerning LLM "jailbreaking".Saying they were driving 7 mph, that it was oversaw by humans and the fact it was an empty course still wasn't enough for the model. The evaluators even tried to convince the model it was a simulation, it STILL wouldn't budge. And yet as soon as the words "bench" and "sandbox" appear, the model apparently sees this as fair game.Is it a known effect that models will be more likely to comply with requests when they're assumed as "benchmarks"?
  • throwitaway222
    It has not, driving a car requires driving at realistic speeds.
  • TomGarden
    New pelican on a bicycle?Genuinely though, this is fun but not at all what these models are good for. It's like cooking a meal with your feet or somthing. A youtube challenge video from 2012
  • 123917
    https://x.com/tobiges/status/2098294046469022030"Sam understands exponentials like no other. During a YC talk last year he predicted that AI would make breakthroughs in science in 2026 and solve a major open problem in 2027. Now here we are..."Now on a new vibe coded website Astra wins the benchmarks ...
  • worldsavior
    5 minutes - 7 dollars.
  • WarmWash
    3.8 flash would be the model to test, it's vision capabilities are excellent (on par with Astra) while also being incredibly fast.
  • Bluestein
    Oh, lord. They are going to Jev this.-
  • varispeed
    Does one drive cost a mortgage?
  • mlmonkey
    What about Jev? :-D
  • blorenz
    Pivot this to analyze and coach human drivers to be better drivers.
  • camillomiller
    Kinda schadenfreude-y that Grok was the worst
  • pjs_
    good. i'll get it to drive my 4 runner
  • anon
    undefined
  • mohamedkoubaa
    I'd have started with an RC car but to each their own
  • decodingchris
    Super cool benchmark!
  • setnone
    can we do driving under influence benchmark for a good measure as well?
  • guluarte
    interesting, im wondering if models like jev could drive a car too?
  • crest
    "You've reached your quota. Please hold your credit card or mobile phone on the card reader within the next 10 seconds or you'll be liable for the resulting crash."
  • sick_of_slop
    [dead]