Nevermind. I fixed it. A little fiddling and some work with a canker and I've got turns as crispy as FSD with no navigation. There's absolutely 0 reason for me to type in an address for FSD. Just follow my blinkers.
This is the magic of FOSS. @comma_ai
today was my last day @comma_ai. not a single day went by where i didn’t learn something new!
thanks for having me!! enjoy some fun photos throughout my internship
Ok, we hear you.
If you're interested in being part of the comma installer network, email [email protected].
We'll work with the top 5 reach-ins to setup a pilot program to try this out.
We try other systems, but we barely have enough time/resources to distill our big models into small models as-is.
We do look at the approaches though, and in many cases, you can get a good sense of capability from that. We're confident iterating on our current stack will scale to capability far beyond what we have now.
Cool release from @nvidia
> 3x bigger than our current Chestnut model
> 90x bigger than the on-device model
> Our current world model is 2x bigger though (4B)
Should we stream once we get it driving on Chesntut?
Meet NVIDIA Alpamayo 2 Edge, a 2B-parameter reasoning VLA model designed for real-time, in-vehicle deployment on NVIDIA DRIVE AGX Thor.
Generate driving trajectories and causal explanations powered by adaptive reasoning.
Learn more 👉 https://t.co/j9ZrEqGuIS
Try it out on @huggingface 👉 https://t.co/u3ZLGwVADW
Cool release from @nvidia
> 3x bigger than our current Chestnut model
> 90x bigger than the on-device model
> Our current world model is 2x bigger though (4B)
Should we stream once we get it driving on Chesntut?
Depends on what you mean. These terms have been muddied.
If you mean a robotaxi service that moves the driver offsite somewhere and works in a handful of carefully selected cities, that’s not on the roadmap.
But if you mean a superhuman driving agent that takes you to any Taco Bell in the world, that’s the goal.
https://t.co/7CrggZmSgI