The world is not zero sum. People can create something out of nothing, and many do. Should be encouraged more.
6
23
309
68,464
Awesome to see the openpilot community flourish!
custom model trained via openpilot.distill can drive down the road in real life :)) only 50h of real footage plus world model rollouts pose head is still gaslighting the kalman filter... more work to do
2
51
1,705
I'm not worried AI will end humanity, and you shouldn't be either. But I am worried it's going to make the future lame. History has been wonderfully exciting, and I want the future to be equally so. I don't care about your P(doom), but let's make sure your P(lame) is low.
1
71
2,889
You can install openpilot on a 2019 corolla, an 8 year old car, and it will stop at stoplights for you. If @comma_ai didn't exist, old cars would almost certainly never get capability like this. And most people would claim a project like openpilot could never exist. Many cool things only exist because a few people decided it should. You can just do things, and more people should!
11
26
278
12,421
The new location will not be in California, because power is criminally expensive here. We'll need robots to remotely fix things sometimes, also hiring people to make those robots work!
Our GPUs have outgrown our little San Diego office. In 2027 we're starting up a bigger better datacenter with more GPUs. We are hiring engineers to work on this. If you know linux and like sshing into machines that cost more than a Ferrari, you might be a good fit.
9
3
116
5,514
Our GPUs have outgrown our little San Diego office. In 2027 we're starting up a bigger better datacenter with more GPUs. We are hiring engineers to work on this. If you know linux and like sshing into machines that cost more than a Ferrari, you might be a good fit.
46
14
540
35,621
More info on cluster: blog.comma.ai/datacenter/ Hiring both interns and FT engineers. FT salary 100-200k. My email: harald@comma.ai
1
41
3,083
I've always been an AGI/foom skeptic, but I admit modern LLMs feel a lot smarter than I expected they would. It's hard to find things they cannot do. Yet all real-world value metrics (GPD, life expectancy, production, ..) are stable and indicate this is just technological progress as usual. I find it hard to reconcile those two things. My best guess is that we just don't understand intelligence and value-creation. And that our primitive intuitions about them are easily fooled, but time will tell.
21
8
155
12,201
openpilot's longitudinal policy has 2 modes. Traditional ACC, and full e2e mode where the driving model decides everything. Including highway speeds, slowing down for curves, and stopping at lights. Since this year users are preferring the e2e mode! Time to go out of beta.
3
4
59
3,495
By Christmas we will remove the two modes, and e2e will be the only mode openpilot supports.
1
13
588
This is incredible news. Big companies having monopolies on cyber capabilities would be terrible. The future is much brighter when power is decentralized.
4
70
2,007
Robotics and self-driving will go this way too. It will take a while, but open-source will eventually dominate. Hopefully openpilot will speed this along!
1
37
1,426
ChatGPT can teach you how to use the autopilot while flying. Pretty neat!
3
43
2,230
Are we supposed to be feeling the AGI already?
3
24
1,455
Nice work! Cool to see people use comma 4s for this type of stuff, the power of open-source!
We gave ChatGPT, Claude, and Grok control of a real Toyota Corolla 🚗, steering/gas/brakes, no human driving (just a foot over the brake). Only one model was able to complete our entire driving course. Introducing DrivingBench. 🔥⌛️🏁
2
3
61
4,511
Brought up mimo-2.6 flash and glm-5.3 flash in our datacenter. These new models are insanely efficient, they run great on just one 5090 machine. Only a year ago there were no good LLMs to run on these machines.
2
1
45
2,649
The clanker found I have a rare mutation which the literature says causes with brain atrophy and eventual paralysis starting in your mid-forties in 100% of studied cases. ncbi.nlm.nih.gov/clinvar/RCV… A bit scary, but the priors were in my favor. My parents seem to have intact brains, and de novo mutations are extremely rare. I got their DNA analyzed and confirmed one of them had the mutation with no symptoms, so I should be fine! Moral of the story is more people should publish their DNA so the literature can improve!
LLMs are great at gene analysis! Genome sequencing has been a thing for a while, but the analysis software was mostly useless. But now codex can do it for you! And once you've gotten over the fear of having a scary genetic disease, there are cool things to learn.
5
1
77
7,188