| ▲ | jyoung8607 an hour ago |
| 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) Will 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. |
|
| ▲ | aditya-ramabadr an hour ago | parent | next [-] |
| Great point! Yeah latency was one of the biggest issues here. To cope with that (and for safety reasons) the cars are driving at extremely low speeds. They also get timestamps with every tool call output etc so they can, in theory, "in context learn" about their own latency and choose motion durations and control how fast their iteration loop is to some extent. But yeah, this is just sort of a fun benchmark to see how good frontier LLMs are out-of-the-box at driving a real car, and probably not actually practical any time soon. -Aditya, Tobias, Simon |
| |
| ▲ | jyoung8607 34 minutes ago | parent [-] | | To clarify my parent comment, I think it was an interesting experiment and seems like it was done well, and it may well be informative about what various frontier LLMs could do with recorded or world model footage. My only point is to say this sort of experiment is where it ends. Neither Anthropic nor OpenAI will be coming out with a "drive your car from the cloud" subscription until we have FTL communication, meaning never. | | |
| ▲ | sashank_1509 24 minutes ago | parent [-] | | Is it plausible they can use the large GPT model, to distill a smaller car driving model only from it and then run that onboard. Seems like that will solve all your issues. |
|
|
|
| ▲ | ivanjermakov an hour ago | parent | prev | next [-] |
| > otherwise you can't react I'm far from neuroscience, but humans don't need to operate at 20Hz to drive a car. And human reaction latency (event to measurable action) is often over 1s (under 1Hz). |
| |
| ▲ | chaos_emergent an hour ago | parent | next [-] | | The reaction latency you’re referring to for humans includes perception, planning, and actuation, I’d separate that from the concerns of the hardware, which are mostly about actuation frequency. From what I understand about AV (as a non-expert!), all three of those steps happen at different clock rates, ie you have a planner that’s updating continuously with observations from sensors at one rate, that planner then issues actions that get picked up by the actuators at another rate. In that sense 20hz should really be compared to human reflexes without perception and planning; in scenarios where one is anticipating an action, response time can be as low as 150ms. in that context, I think 50ms/20hz is plenty reasonable for an automated driver. | | |
| ▲ | gpm 24 minutes ago | parent [-] | | In circumstances where one is maintaining grip or muscle tension (e.g. steering a car) I believe human response time can be more like 50ms. Which perhaps unsurprisingly lines up with the 20hz figure pretty close to exactly (we built cars controls so that they're controllable by human reflexes). Though you can't convert between hz and latency, all 20hz tells us is that it adjusts 20 times a second, not how long it takes from sensor input to be fed into a particular choice of adjustment, there could be (and actually almost certainly are) multiple adjustments in flight simultaneously with the adjustment actually being applied being calculated from old data (both in humans and automated substitutes). |
| |
| ▲ | mirrir 38 minutes ago | parent | prev | next [-] | | I'm not an ornithologist but birds don't need to consume jet fuel to fly hundreds of miles either. | | | |
| ▲ | bonsai_spool an hour ago | parent | prev | next [-] | | > but humans don't need to operate at 20Hz to drive a ca This is not a helpful statement unless you can claim what speed human sensors do work at. And it's going to be faster than the latency of $(sensor + server round trip) Hertz, not getting into LLM processing time. | | |
| ▲ | Groxx an hour ago | parent [-] | | It's also not subject to signal loss issues like anyone who uses a phone is quite familiar with. Unless you have narcolepsy. |
| |
| ▲ | cozzyd an hour ago | parent | prev | next [-] | | Let's see how well you play counterstrike with a 100 ms ping... | |
| ▲ | replygirl an hour ago | parent | prev [-] | | reaction latency doesn't cover everything. the round trip from trigger to action is a few hundred ms at best, yes, but to enable that we are processing inputs at ~30hz minimum and integrating at ~5hz. you would total your car pretty quickly if you couldn't constantly adjust |
|
|
| ▲ | odo1242 29 minutes ago | parent | prev | next [-] |
| You can see this in the photos, it took over five minutes for the cars to get around the cone course. |
|
| ▲ | Onavo an hour ago | parent | prev | next [-] |
| > 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. Well, if the massive cloud models that are generalized and have a world model that's good
enough, you can just distill them into smaller models. As a point of reference, the current gen of Tesla FSD models only have 1B params. They are tiny by LLM/VLM standards. |
| |
| ▲ | chaos_emergent an hour ago | parent [-] | | Wow, I had no idea that they are so small, that’s incredible! Really goes to show how much visual information can be compressed. | | |
|
|
| ▲ | ramesh31 an hour ago | parent | prev | next [-] |
| Perhaps there's a synthesis to be had though. Eyes, control, and safety critical features on the hardware, higher level decision making to the cloud. Openpilot's biggest weakness has always been in the very "robotic" way that it drives, which is technically correct but causes frustration for other drivers. Deciding "should I pass this car" is a fundamentally different question to "can I pass this car", or "what is the actual safe speed and following distance given the current traffic conditions and weather". |
|
| ▲ | simianwords 44 minutes ago | parent | prev | next [-] |
| How are you so sure that latency can't be improved? Sol can run on cerebras and we may get enough efficiencies that Astra can also be run locally. |
|
| ▲ | miltonlost an hour ago | parent | prev [-] |
| [flagged] |
| |
| ▲ | burnte 44 minutes ago | parent | next [-] | | I'm not that commenter, but I wouldn't were I that person. There's a lot more self-responsibility involved with a Comma system than what Tesla advertises as "Full self Driving." It's the difference between blaming Ford for bad factory breaks versus aftermarket parts the consumer made themselves. | |
| ▲ | jyoung8607 an hour ago | parent | prev [-] | | This question reads a little ambiguously. The first way I could read it is that you're genuinely concerned about my mental health as a mainly-volunteer open source developer. The second way to read it is a direct accusation. Can you please clarify? |
|
