‹ BackHN Continuity

Thread

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

316 points · 251 comments · plurby

  1. valine · · focus · HN ↗
    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.

    1. atonse · · focus · HN ↗
      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.

      1. overgard · · focus · HN ↗
        Totally solved: <a href="https:&#x2F;&#x2F;electrek.co&#x2F;2026&#x2F;09&#x2F;15&#x2F;tesla-four-fatal-driver-assist-crashes-july-2026&#x2F;" rel="nofollow">https:&#x2F;&#x2F;electrek.co&#x2F;2026&#x2F;09&#x2F;15&#x2F;tesla-four-fatal-driver-assis...
        1. atonse · · focus · HN ↗
          You added &quot;totally&quot; - as others have said, I don&#x27;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&#x27;re putting their money where their mouths are.

          The idea that Tesla&#x27;s FSD is not ready for the mainstream is quite outdated, given that tons of Tesla owners are already using it daily, not just your early adopter types.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.