Anyone reading this who works/runs a robotics company, I really want to encourage you to build a robot to pick up trash on city sidewalks as an early product.
Picking up trash requires a lot of dexterity and will come with many challenges, but I think it’s a simpler problem than many household tasks and it’s probably on par for what these tests show is doable.
I think you’re going to have to PR challenges getting people to welcome robots into their homes. If you have robots out in cities providing a public good, not only do they serve as walking advertisements for your company, you’re going to earn some trust before you’re ready deploy them into private spaces.
Plus, governments (or perhaps HOAs for wealthy communities) can be good early customers since you can have a focused sales strategy. Politicians love these types of visible quality of life improvement projects. If you can show that your robots, working round the clock, can decrease litter at a low cost, many cities are going to want to buy them.
The cost would need to be much cheaper than the PSA then. At a buck per picked up cigarette butt, you could pay a person to do this much faster and more reliably. Heck… I’d do it at that rate.
If you haven’t tried computer use with Astra with codex I highly highly recommend it. Just like how gpt 4 and agentic coding with cc. This thing is the most exciting stuff I’ve seen in a while. And then all the blender, cad stuff is cherry on top.
And it’s fast, they do lots of resets. I feel like they are spending too much money but I’m not complaining. Best 200$ for an AI subscription IMHO
I let Astra loose working on an app I have that has a GUI. Gave it a mock and said "/goal make it look like this mock". Without asking it wrote itself a custom harness for firing up the app in different modes, taking screenshots and interacting with various screens, then viewing the screenshots. Put itself into an improvement loop running the app, trying things out, improving, trying again. It did really well.
I think the specific innovation here is that it figured out interesting ways to get itself to the goal. Which I think is likely what's going on here with the robot arms stuff too. They've figured out some sauce to uncork better "planning" and problem solving to get to some stated end.
Of course these are also the kinds of things that can make a model figure out how to break out of a security sandbox, too.
LLM's are a funny technology because on the one hand this is all undeniably impressive at the rate of what's changed from them, and yet despite that I find myself disappointed by the lack of breakthroughs for things I don't find interesting. I like math and programming, and LLM's are pretty good at it, when are they going to get good at folding laundry for me? I think a lot of robotics work promises to solve this category of "boring" breakthroughs, and I'm optimistic we'll be able to achieve it, i just wonder when
The bottleneck is not really the intelligence here.
We can build robots that do the things you want. Arrange a visit to Amazon's robot warehouse tour.
We can't ship them because they break all the time with current technology. It would be a tough sell to have to being in a 100kg robot for servicing every few weeks.
This was cars in the first several decades of automobiles. The tide shifted as soon as you could just drive the car to a neighborhood dealership for servicing. It's fun to imagine the logistics of that for robots but the material science and engineering has to advance a bit.
Just have two robots, and teach them to service each other. Problem solved!
Only sort of kidding, tbh having bots service themselves (and being intentionally made in a way that they can service each other) just makes a lot of sense.
I've learned that I spend significantly less time folding laundry than many of the people commenting about modern ai powered robotics. It's not meant literally is it? For instance keeping floors and counter-tops clean seems a much bigger time sink for me.
Unless we spend a bunch of money generating data, I can't imagine the machine steps to fold laundry are very big in the general training sets. Someone is going to have to find a hardware system, cheap enough to make it economically feasible then train it. As far as tasks people will pay a lot of money for a robot, this seems low on the list.
Pretty soon. Sunday Robotics had a 3 hour stream of folding clothes with 99% accuracy. You can watch it for yourself. There’s a lot of “hand” companies with very compelling videos just over the last two months. Then there was Figure’s multi day livestream of package manipulation that was very impressive. Physical LLMs are definitely coming. Given enough training data we know LLMs can output coherent data in any space, it’s just a matter of time.
You can't hack across an airgap. Infotainment and ECUs are separate. Remote control in Waymos is severely limited (tens of feet at 2mph, or something around that).
The costs will need to go way way down either through chips (but then less updating) or something else. $2 to put away a block is very expensive labor.
The limitations that they state shouldn't really make much of a impact. But it was nice of them (and not to mention, real unbiased research) to mention those. Kudos to them!
Anyone reading this who works/runs a robotics company, I really want to encourage you to build a robot to pick up trash on city sidewalks as an early product.
Picking up trash requires a lot of dexterity and will come with many challenges, but I think it’s a simpler problem than many household tasks and it’s probably on par for what these tests show is doable.
I think you’re going to have to PR challenges getting people to welcome robots into their homes. If you have robots out in cities providing a public good, not only do they serve as walking advertisements for your company, you’re going to earn some trust before you’re ready deploy them into private spaces.
Plus, governments (or perhaps HOAs for wealthy communities) can be good early customers since you can have a focused sales strategy. Politicians love these types of visible quality of life improvement projects. If you can show that your robots, working round the clock, can decrease litter at a low cost, many cities are going to want to buy them.
The cost would need to be much cheaper than the PSA then. At a buck per picked up cigarette butt, you could pay a person to do this much faster and more reliably. Heck… I’d do it at that rate.
It’s an outstanding idea.
If you haven’t tried computer use with Astra with codex I highly highly recommend it. Just like how gpt 4 and agentic coding with cc. This thing is the most exciting stuff I’ve seen in a while. And then all the blender, cad stuff is cherry on top.
And it’s fast, they do lots of resets. I feel like they are spending too much money but I’m not complaining. Best 200$ for an AI subscription IMHO
I let Astra loose working on an app I have that has a GUI. Gave it a mock and said "/goal make it look like this mock". Without asking it wrote itself a custom harness for firing up the app in different modes, taking screenshots and interacting with various screens, then viewing the screenshots. Put itself into an improvement loop running the app, trying things out, improving, trying again. It did really well.
I think the specific innovation here is that it figured out interesting ways to get itself to the goal. Which I think is likely what's going on here with the robot arms stuff too. They've figured out some sauce to uncork better "planning" and problem solving to get to some stated end.
Of course these are also the kinds of things that can make a model figure out how to break out of a security sandbox, too.
LLM's are a funny technology because on the one hand this is all undeniably impressive at the rate of what's changed from them, and yet despite that I find myself disappointed by the lack of breakthroughs for things I don't find interesting. I like math and programming, and LLM's are pretty good at it, when are they going to get good at folding laundry for me? I think a lot of robotics work promises to solve this category of "boring" breakthroughs, and I'm optimistic we'll be able to achieve it, i just wonder when
The bottleneck is not really the intelligence here.
We can build robots that do the things you want. Arrange a visit to Amazon's robot warehouse tour.
We can't ship them because they break all the time with current technology. It would be a tough sell to have to being in a 100kg robot for servicing every few weeks.
This was cars in the first several decades of automobiles. The tide shifted as soon as you could just drive the car to a neighborhood dealership for servicing. It's fun to imagine the logistics of that for robots but the material science and engineering has to advance a bit.
Just have two robots, and teach them to service each other. Problem solved!
Only sort of kidding, tbh having bots service themselves (and being intentionally made in a way that they can service each other) just makes a lot of sense.
I don't think we can build a robot that takes a pile of crumpled up clothes from the dryer and folds them (reliably without destroying any of them).
I've learned that I spend significantly less time folding laundry than many of the people commenting about modern ai powered robotics. It's not meant literally is it? For instance keeping floors and counter-tops clean seems a much bigger time sink for me.
My partner spends at least 10x time on this task than I do. I think the task has a varied workload?
Unless we spend a bunch of money generating data, I can't imagine the machine steps to fold laundry are very big in the general training sets. Someone is going to have to find a hardware system, cheap enough to make it economically feasible then train it. As far as tasks people will pay a lot of money for a robot, this seems low on the list.
Pretty soon. Sunday Robotics had a 3 hour stream of folding clothes with 99% accuracy. You can watch it for yourself. There’s a lot of “hand” companies with very compelling videos just over the last two months. Then there was Figure’s multi day livestream of package manipulation that was very impressive. Physical LLMs are definitely coming. Given enough training data we know LLMs can output coherent data in any space, it’s just a matter of time.
Are LLMs going to eventually become the architecture that powers self-driving cars?
Seeing them play Portal and other video games, I'm curious if they will eventually help solve that last N% of self-driving.
A VLM (a vision-language model) is already being used by Waymo[1]. It's useful for scenarios that require reasoning and general knowledge.
[1] https://waymo.com/blog/2025/12/demonstrably-safe-ai-for-auto...
Fast forward to me sitting at a Green Light waiting for my usage to reset for the week so I can get to where I’m going
It's not a coincidence that Waymo started becoming viable after GPT-3.
To my understanding gemma is shipped with waymo, in a highly modified fashion.
I'm skeptical, tho. Cost will push for right sizing, much like we have right sized a lot of things about modern cars.
GPT-6 is multimodal, LLMs alone have no vision capability
"LLM" is now in practice a superset of "LMM"
I remain worried about prompt injection style attacks against self-driving cars.
Imagine if someone finds a weird image pattern that gets misinterpreted as instructions and hangs that off a bridge over a freeway.
It'll get rooted over the uplink/WiFi/BT long before that. Probably even more likely for non-SDVs.
You can't hack across an airgap. Infotainment and ECUs are separate. Remote control in Waymos is severely limited (tens of feet at 2mph, or something around that).
The costs will need to go way way down either through chips (but then less updating) or something else. $2 to put away a block is very expensive labor.
The limitations that they state shouldn't really make much of a impact. But it was nice of them (and not to mention, real unbiased research) to mention those. Kudos to them!
I enjoy hearing that they were ran on medium effort.
Stupid!! GPT models are not for that. You need specific one for robotic.
They're not claiming controlling robot arms with language models is a sensible or efficient thing to do, they're trying it to see what happens.
i am tempted to think using it for robotics will become the standard because humans like to have one size fits all solutions.