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!
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
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.
I feel the iPhone or ChatGPT moment for robotics is coming soon. Lots of different companies doing interesting things. What’s missing is somebody putting it together into a compelling package.
I'm starting to think that a ChatGPT moment for robotics would require abandoning the current brute force approach to artificial intelligence. ChatGPT's trick was simply more data and compute. A stochastic parrot will eventually become very impressive. But we don't have an equivalent of billions of lines of code for robotics.
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.
I think the parent's point - and what I more or less agree with - is that the problem is the hardware.
Human arms and hands are incredibly intricate. Reproducing their facility with hardware requires a large number of actuators and finicky fine parts. This isn't a software problem. Industry solves it with maintenance schedules.
There's probably nothing in your house that has as many moving parts as a robot needs. Your car maybe, and pretty much all it does is rotate wheels.
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.
An automated service station could be quite compact; it wouldn't need plumbing, lighting, human-comfortable climate control. Parts can be modular, and when a station gets low on spare parts, a self-driving truck could come by to pick up damaged parts and drop off replacements.
We're not there yet, but I think we're a lot closer than most people realize.
Really? All you need to do to stop this is to stop governments from hiring robot "labor". Surely a democracy can make that decision, even when it means paying a little bit more, no?
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.
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.
It's just a general "thing I don't want to do" not the thing that takes the most time. Could be taking out the garbage. It's just an example menial task.
f folding clothes, i wanna just have a robot be my personal chef. the amount of different tasks and capabilities a robot will need to make any meal that I can in my kitchen is huge and i feel like it’s still a while from being solved.
It may sound strange, but cooking is one of the most intense and attention-consuming tasks I encounter.
I have to do it every day too.
So I fully agree with this line of thought... Many a time I have considered that I would happily spend more on a personal 24/7 chef than I ever would on a car. Cars to me are utilities and should simply be efficient and optimized to purpose - food is luxury and taste, it is sublime experience and art.
Maybe that's why I can't make it, treating every recipe like a strict command chain isn't how art is done. Can my taste buds be scanned?
I mean honestly anything is taste and art. People care about very different things. Some people see their clothes as the biggest expression of themselves, whereas others don't care about their clothing but see their cars as art and a special experience thats separate from the purpose.
But yeah, I think a lot of food is just practicing. And if possible, learn from someone who's food you do really like, and experiment. Just try making some dish you really liked, you'll be surprised at how far you can get.
future is on the way, three to four generation ( one each year ?) will unfold this, primarily quantum computer improving material and battery, humanoids becomes standardised and modular enough to be easily replaceable ( think ibm pc ) ( most components are simple injection moulded advance plastics , mass produced in some corner of china, self detection of wear and tear and self replace that part ), other is optical computers ( 100x lower power x 100x speed = local inference ), problem is, when this will become reality, who will benefits more ? who will hold moat ?
It's because existing models are a brute-force approach to intelligence. With enough data and compute, a stochastic parrot will become very impressive.
But with robotics, there's no pre-made dataset that can be parroted. Notice that these datasets, e.g. how to fold clothes, need to be created by humans. That's as if humans needed to write algorithms like quicksort to teach LLMs how to code.
The economic value in automating high skill and expensive labour that the most profitable corporations rely on is what attracts the most investment and effort.
Once you lose your job you'll find plenty of time to do all those menial tasks you hate wasting time on.
Jokes aside, programming and mathematics are just well ordered environments. Already digital and verifiable. Perfect for a GPU cluster to power through.
The real world is big slow and complex in comparison.
The costs will need to go way way down either through chips (but then less updating) or something else. $2 to put away a block is very expensive labor.
Actually, you don't really need a dedicated model as long as you have the proper adapter like the projector model for vision inputs you just need another for robotic outputs, after that it is just a matter of having the training data.
If you haven’t tried computer use with Astra with codex I highly highly recommend it. Just like how gpt 4 and agentic coding with cc. This thing is the most exciting stuff I’ve seen in a while. And then all the blender, cad stuff is cherry on top.
And it’s fast, they do lots of resets. I feel like they are spending too much money but I’m not complaining. Best 200$ 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.
I tried out Opus 5 on a Bevy game app and was really surprised at how capable AI has become at testing visual applications without even being prompted to. It wrote itself a mini testing harness in the form of various startup flags. Then it would use them to setup game scenarios and play through them using mouse and keyboard. It would do this while implementing or debugging features. With gameplay time acceleration as one of the flags, it became quite fast at testing and debugging.
Not to say it was perfect, e.g. sometimes it would get temporarily stuck in a testing loop or it would test scenarios that didn't necessarily seem reasonable. But overall rather effective and capable. This was for a city building game so pre-scripted builds, even if by AI, are likely much easier to create and execute than say playing an ARPG.
I got Astra to build an interactive website that provides developers with an atlas of our source code, giving it the Helm charts that describe our cloud services and telling it to work backwards to the source code that runs everything. The product is insanely amazing, and it got it right in one shot. The next shot: create a daily refresh where any updates to the code repositories are picked up and used to update the atlas.
Our developers and their agents will never long for a road map the next time they need to build something that touches code across multiple repositories. This is the kind of documentation product that nobody ever had time to build in the olden days. And now, we can get it on a Saturday in about 20 minutes.
It is likely too specific to our particular orchestration approach to be useful as open source. But the recipe is replicable.
You can just paraphrase this prompt:
“Starting with our Helm charts, which you will find in /folder-of-charts, build an interactive website that semantically relates all of the components of our cloud services.”
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.
Same for recycling. A robot that could sort through trash would be phenomenal. You need computer vision, maybe other sensors and also dexterity. After visiting a recycling facility I think nobody should have to work there. It’s just horrible.
As a tech demo sure. But the current tech for this is much better where you just have a camera pointing at the trash falling, and either flipper paddles or air jets to push the trash in to the correct buckets as it’s falling.
I feel like robots that could do this with 100% accuracy might shine too bright a light on how well recycling currently works. And I say that as a proponent of the three Rs.
> If you can show that your robots, working round the clock, can decrease litter at a * low cost *
The idea sounds good, but I'm curious about the "low cost" part. How do you account for vandalism and theft? A sidewalk robot seems like an easy target for being damaged, stripped for parts, or simply stolen.
In SF they would be taken quickly by the homeless for parts, probably the batteries most of all. That and rummaged through for drugs, or repurposed to deliver drugs.
Is this what happens with scooters and lime bikes etc? Because it always strikes me that they’re easy targets for cannibalism yet nobody seems to do it.
It was common for people to vandalize and throw them in bodies of water for a while before people got used to the idea. I still occasionally see some repurposed from time to time
Cities with the social order required for robotic street cleaning rarely require robotic street cleaning. One might as well suggest a novel heart surgery that works only on healthy patients.
China has very little street crime but they pay street cleaners very regularly. You can actually find videos on YouTube. I just watched one with a 65-year-old man who manages 600m of street and has managed the same street for 28 years. Just using big brushes, dust pans, and putting it all in garbage bins. the city pays him between $600 and $800 a month in USD.
Coincidentally, Asia is a lot more receptive to AI as well. Turns out having strong job protections means that companies actually need to figure out how to make humans more productive with AI, instead of replacing them.
> much less protections in terms of well-being (no federal minimum wage, absurd work hours as standard, etc)
There absolutely is minimal wage but is set by local governments, because different places have different cost of living.
There are better protections for work hours for salaried workers than America. Anything above 40 hours get paid at 1.5X and anything above 60 hours get paid at 2x.
And talking about absurd work hours, SK and Japan aren't better than China.
>talking about absurd work hours, SK and Japan aren't better than China.
On paper, no. Japan has overtime bonuses too, but you're culturally discouraged from reporting overtime. So 12 hour days are common with no OT. And thats not including "optional" after work outings.
Yet, it's also not uncommon for Japan to bring about the "appearance" of working more than really working. Whether you judge that appearance of work as more or less stressful than China's work standards is a more personal question.
Either way, my main comparison was Asia to the US rather than countries within Asia. US has higher salaries, better minumum wage (but still nowhere near good), and usually better hours. But stability without unions is non-existent as we've seen the past decades.
Most of my understanding is based around studying Japanese law, so I wouldn't extend it to all of asia. But the main protection is that much of Asia is not at-will employment. So you can't easily create mass layoffs like the US without good reason (some regions won't do that because wage floors are pathetic or non-existent, but it's still some protection).
So, im going to address this low effert, uninformed post first, but the longer part of this will attempt to be informational to the larger branch under discussion here.
TLDR; not really trash in the streets anywhere by any reasonable measurement and nowhere near 'plenty' unless the definition of 'plenty' is 'some, somewhere, sometimes.' & Conversion rates don't matter when discussing minimum wage rates, only the local purchasing power matters.
Here's the longer than anyone might expect who doesn't recognize my posts;
Trash may sometimes appear in a few places, mostly in larger inner cities with significant international populations. In my town, and even in the larger regional metro areas, just about the only places I see actual litter are where tour buses full of international tourists deposit daily crowds or where a high speed road passes through forested areas without much concurrent traffic and so people feel that it is acceptable to toss drink bottles and food wrappers out the window unseen. The rest is remarkable for the general lack of any trash on the streets.
It is a common sight in almost every town and city, early in the mornings, to see any number of people actively sweeping the sidewalk AND street in front of homes or businesses. Some will be washing with a brush and clean water.
For nearly the entire country, trash is collected from a designated bird and vermin proof cage or box from every block on most weekdays, on a weekly and monthly rotating schedule, sorted into recyclables: with different days for plastics, paper, small metal, appliances and fabrics, and actual 'trash' which is restricted to burnable foodscraps/paper products which are too soiled for recycling and which do not contain glossy or metallic dyes.
If the pickup schedule is inconvenient at your house, or if your volume of recyclables isn't worth spending 35jpy for a clear rash bag [which is how they manage funding the collection: through region specific trash bags of are clear plastic with color coding for which type of waste belongs in them that you may purchase at nearly any grocery or convenience store] there are sorted recycling bins near the main doors of every grocery and convenience store - just drop off on your way in for shopping.
My wife and I do frequently collect and recycle litter from two areas, because one of them is the walking gardens around a shrine which we wish to see remain mostly free of cigarette butts, and the other is a roadside forest of beech, black walnut and chestnut trees. We visit there regularly, collecting for some extra variety in our diet the nuts, sansai (wild greens) and edible fungi that grow in the forest. Collecting the trash haul is no small part of our biweekly free time in the late summer and fall.
Over this last year, as we have continued working along both sides of a 3km stretch of trees it is remarkable how little new trash is occurring. This seems to match our initial observation that the volume of rubbish was of varying ages and had accumulated over a significant length of time since the last cleanup of this nominally 'public domain' patch of forest. [It is a local land trust with the responsibility of fire prevention and otherwise is a Satoyama designated resource for exactly this kind of community wilderness light impact harvesting - which is why there isn't a designated trash cleanup scheduled but once every 4 to 5 years]
Otherwise the amount of 'trash in the streets' is very much limited to inner city and is one of the reasons underlying growing popularity of tightening of immigration regulations. Not saying it doesn't happen in smaller cities, but rather most of Japan generally engages in cleaning up as soon as they notice any trash. The total of loose trash is remarkably lower than anywhere else I have been, and we do travel to other places fairly regularly; including Taiwan, Thailand, Malaysia in the last few months. None of the clean corners of those places is ...
Was just in a Waymo in SF and we were attacked by a gang of cyclists repeatedly swerving at and trying to cause our waymo to crash. Really powerless feeling. And they were doing this knowing humans were inside. I don't pretend to know their motivation other than perhaps misplaced social rage, but I'd imagine a litter robot would be immediately destroyed.
Indeed, I was surprised to hear about “Lowell students” robbing people on Muni and “bicyclists” causing trouble in Mission Bay but when I observed some of this anti-social behaviour (when I saw them they were doing wheelies and swerving at people walking) I was rapidly able to discern why the statements were relatively vague as to the categorization.
I suppose it shall be the case for the short term at least that we must admit that “humans” really cause harm. Though perhaps that’s over specific and I should recognize that most crime is committed by eukaryotes.
The motivation is that they keep getting away with it. And they're going to keep getting away with it until society decides we're going to stop tolerating shit like that.
Then people will say "you're doing this for the rich, and say it can't be done for the poor". Not even for long-term ill or old people living in poor areas.
Hmm never seen that in a residential neighborhood, is that a thing? Typically there is not a trash problem simply because the residents are careful enough. Trash doesn't just appear out of nowhere
The cleaning robot might still be a good test bed. But I suspect if you are only in it for efficiency, you would use something like a street sweeper truck. Just like the dishwashing robot that everyone uses at home (the humble 'dishwasher') doesn't use robot arms to mimic how humans wash dishes.
Btw, Singapore shows that we already have proven, low cost techniques for keeping cities clean without robots.
I’ve had exactly the same idea! Living in LA I sometime imagine how the city will look like in hopefully ten years or less when robots pick up all the litter! Hopefully there will also be landscaping robots and sidewalk/road repair bots too.. those three pretty much are what you need to turn any rundown neighborhood into a sparkling oasis it seems. My other near term idea is just robotic city trash cans, that slowly crawl down the sidewalks on a loop and empty themselves into a big bin in the alley or whatever as part of that loop. I think people probably wouldn’t mess too much with the litter bots either, especially if they work a lot on the sides of freeways. Also people don’t seem to mess too much with the cocos out there delivering food three blocks..
> I think you’re going to have to PR challenges getting people to welcome robots into their homes.
I think it's important that someone point out this isn't a 'PR problem'. It's a practical resistance to commodified surveillance. All these domestic robotics companies train on video of users homes, many sell such data, each and every one are a vector for state domestic state surveillance. Not to mention criminal hackers, stalkers and others with an interest in who is at home when and what precisely they are doing. Short of having non-internet connected, locally processing domestic robots - something unlikely to exist in the foreseeable future - they are a privacy nightmare. Bad as google home, alexa and such devices are for privacy - a walking, controllable, camera and set of mechanical arms running loose in a home is infinitely worse.
It is absolutely a PR problem. Privacy is a real concern, but it's the PR that companies are scared of. As, say, Flock have been starting to find out lately. Public backlash matters.
And PR is the problem you have to overcome for people to let smart devices into their homes too. For instance, people started avoiding Ring cameras once it got out that they're a privacy nightmare -- that's PR. Sure, the people that avoid them care about privacy -- that's why they're listening -- but PR is the reason they even had anything to listen to. Likewise, PR is how people get creeped out by robots scanning their homes. They never wanted that, of course, but they weren't creeped out until they learned about it. That's PR. Now people are wary to let any new devices into their homes, especially robots, because of historical PR like this. And so now it is a PR problem to get people to give you a chance in the first place.
Well, it is a PR problem. It's bad for business to cause a crime spike... that's my point.
I never said focus directly on downstream. I thought it would be obvious that I'm talking about why you bother with upstream, because the downstream effects are important.
Clearly I phrased something very wrong because it looks like everybody is assuming I'm saying that you should do as much bad as you can possibly prevent people from noticing.
It's one of several downstream problems, including poorer quality of life by various metrics. By emphasizing a PR problem for businesses more than other human problems downstream or the root problem, you are demonstrating priorities that prosocial humans viscerally disagree with.
I think internet people care about some theoretical surveillance angle more then anyone else actually does. People hire cleaners and tradespeople into their homes all the time.
The practical problems with robots are effectiveness, cost and safety in roughly equal parts.
> People hire cleaners and tradespeople into their homes all the time.
It's very obvious that there is a difference between a single person that you can personally vet, and something that records videos that can be shared anywhere.
> I think internet people care about some theoretical surveillance angle more then anyone else actually does.
Yes, that's usually the case. However in the very current time of surveillance resistance with the de-Flock movement, I think there is increased mainstream awareness of the issue.
I think you’re partly right: normal ‘non-internet’ folk care less about such things… until a reason to care is demonstrated.
Take the recent anti-Flock actions - it’s probably mostly not ‘internet people’ going for evening walks with their angle grinders. Everyone starts to care about privacy when it really becomes invasive.
Likewise, people might be fine getting their elderly parents a robot to help out with household tasks, until intimate stolen videos start appearing on realgrannies.com or similar.
Sadly we're all internet people, and have been for about 15 years. If you mean people on Hacker News... Then yes, obviously they're by and large better informed about the reality of surveillance, government and corporate, than most. Nothing theoretical about any of it. Unless we fail to remember the content of Snowdon's leaks.
I've been thinking a lot about what it would look like to support verifiable/auditable guarantees around data exfil/capture for this class of use.
I don't think it's enough to pinky-promise that you aren't sending a dragnet of video with facial capture etc back to the mothership, I think you really end up wanting auditable proof that nothing sensitive can leave the robot or at the very least a no-logging hot-path inference loop (e.g. apple's confidential compute).
I would like to run a robotics company. But raising for that is super challenging, because you have high execution risk combined with low margins on the final product. It's like the opposite of what western VCs want to see. That's why this type of company is usually founded in China.
And I disagree with you. I'm pretty sure parents worldwide would love a clean-up robot. You can avoid a lot of the risks by making it work only for empty rooms, which is OK because you need to clean up and let the vacuum robot run anyway (when the kids are away sleeping in their bedroom). There's been multiple attempts at building DYI robots to vacuum LEGO bricks off the floor. (Because stepping on them at night is such an immediate pain point.) Unless your product is soaked in hostile behavior and surveillance tech, parents will probably be happy to buy an in-home cleaning robot, no PR needed.
I think the main issue here is that parents are typically busy, which makes them bad startup founders, which is why they cannot "scratch their itch" and turn it into a business.
=> home cleaning robots do not exist because western VCs don't like it and parents aren't usually startup founders.
> Are you suggesting that wealthy people litter less?
Yes. Well, middle class less than working class at least. And only on average. Also individual behaviour isn't the only factor - they also tend to live in wealthier less dense areas, where councils have more money to spend on keeping things tidy, and there are also people who do volunteer litter picking.
> Are you suggesting that wealthy people can not be vandals?
Obviously not.
> Or are you suggesting that common people are littering vandals?
Not even sure what you're trying to say here. You think I was suggesting that all lower class people are littering vandals? Lol.
This is really stupid tho. There are already robots that are way better at cleaning the streets. This is at least how they clean the dirty af streets in eindhoven after an event literally in one single night. Maybe sorting the trash for recycling... But then you don't need any legs, at most hands. So I don't think humanoid robot would be the way but there would still be the need of vision and hands I guess...
I've been running a project for the last 2 days trying to create a skill for openclaw that would allow control on the adeept tank (a small toy tank with a robot arm).
Let me be frank;
Astra has been UTTER SHIT not just a little, a lot.
It is much more expensive than Sol 5.6 Medium / High and did nothing but write unit tests and write frankly junk code examples:
- In two instances had the direction of the servos wrong.
- Calculated the maximum extent of the gripper wrong, and the closure, so it didn't grip.
- Failed to take into account the gripper requires torque when lifting a pair of socks.
- Failed to actually start testing more than opening and closing the gripper.
- Failed quite spectacularly to calculate camera gimbal extent range correctly, the code was useless.
The test environment has both an onboard ultrasonic for distance, a camera, and a bird eyes view camera while training (only while training).
I've gone back to Sol 5.6 medium/high for the training, it's cheaper and now I'm back to fine tuning, after it had to redo large chunk of the driving code and prevent unnecessary hard stop code kicking in based on the wrong profiling.
It's cost me around 1000 credits, burnt in around 2 hours, looking at video, and photos, and writing bad code. I've also burnt through Regular Plus 5 hour quota in about 30-45 minutes.
There is something deeply wrong with Astra. I can’t quite put my finger on it. On the one hand it is a lot more knowledgeable, which makes sense since it’s a larger model. On the other hand that knowledge doesn’t reliably translate to intelligence or insight. Certainly tasks like 3D modeling it does extremely well. Other stuff like complex coding problems in an existing codebase it stumbles more often than not. This morning it ran around in circles. It implemented a feature, then convinced itself that it should have followed “proper TDD”, deleted all the code it had written and wrote 8,500 LoC of unit tests. At that point I was down to 35% of quota so I stopped it and gave the task to Opus 5.
Really weird model. No idea how it did so well on all the benchmarks.
That's exactly the kind of behaviour I've seen, unbelievable amount of unit tests, and revisiting and revising the same code over and over again.
If I was cynical, I'd say almost like it was deliberately trying to burn quota, even after I told it quota was getting low and to move onto actual physical testing.
Which benchmarks? Only the ones OpenAI cherry-picked.
It debuted as ~same score as Sol on Artificial Analysis. People couldn't accept it so they had to change the formula.
The model is a big step forward only in desktop use and 3D. I really wanted Astra to be great, but for software engineering, Fable is still on a league of its own.
I'm not sure why this has been voted down, it's a counterpoint to the hype with factual anecdotes to back up the claim of it's performance Vs the article itself.
I've got the source and video to prove it too.
I don't know much about robotics engineering, so I just wanted to give kudos to the Robocurve team on this write-up.
Even for an absolute robotics newbie such as myself, the article was interesting to read, and easy to understand. Plus it was straight to the point, with no unnecessary waffle.
I think we need to be honest here. Author is basing it on one small experiment of picking up a block, relies on an whole IK controller pipeline to do the job, and does not compare it to full VLA or WAM models. They then proceeded to extrapolate the token throughput (mind you not the same as controller throughput) into supposed 2029 timeline, from one example.
Thing is even recent Gemini Robotics 2 argues for architecture that has a VLM planner and then a VLA/WAM controller + a local small VLA model when connection disappears. And recent SOTA architectures rely on hierarchical design.
I think this might be a sensible way to go about it. If you were to train GPT-X on robotics data and to output actions, congratulations! you've just made a VLA.
It is enticing for people to just wish for one architecture to do it all, which is why we get stuff like this. I think there is a lot more to gain from modularity and we should not be afraid of specialization.
I’m honestly blown away by Astra, I told it to build me a fairly complex game I’ve been procrastinating on for more than a year and left it running overnight with computer use and full access enabled. Next morning I had a fully functional game built. It downloaded Unity, Blender and GIMP and built all the assets as well as the complete game without me having to do anything, the game is not trivial at all and nor are the assets.
In case you haven't noticed. Almost everything is supply limited in the economy. You cannot currently work and make stuff that gets sold at a supermarket. None of that stuff is American. Or European. Or Russian. Or Moroccan. Yes, maybe the luxury cheese section is local. Maybe the draft beer section. But they are large exceptions, nearly everywhere on the planet.
It's a complete miracle that anyone can have any job today.
So: "how is anyone going to afford robots if no one can work?" Well, exactly the same way as today.
It seems like human movements have the equivalent of small fast models to perform routine actions and balance but the higher brain is able to take over as needed. Is anyone trying to replicate that concept?
It's still shit but I wonder, what is really the thing anyone is trying to accomplish here?
Genuinely.
It's trying to rob people of opportunity to ever migrate and or seek a better life? not just between countries which will very obviously be restricted if actual AGI is ever achieved. Why would you ever give the chance for anyone to come to your country if you do not need their skillset? It would also prevent rural people/town people from going to the big cities.
The obvious end goal is to create a bunch of different "permanent" classes or at least they hope so, I think however you can expect a ton of violence to come from this and people will wish they never invested the resources into this, something beyond what the french revolution ever was, I'm not saying I think it should happen or not, I'm just pointing out the obvious outcome of robbing people of value/worth/dreams in their life.
156 comments
[ 0.94 ms ] story [ 42.3 ms ] threadWe 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.
Human arms and hands are incredibly intricate. Reproducing their facility with hardware requires a large number of actuators and finicky fine parts. This isn't a software problem. Industry solves it with maintenance schedules.
There's probably nothing in your house that has as many moving parts as a robot needs. Your car maybe, and pretty much all it does is rotate wheels.
That's not the case. I've seen folding robots. They require standardized input, only fold one type of clothing and don't do it reliably.
But you can't buy it because it'll break in about seven days.
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.
We're not there yet, but I think we're a lot closer than most people realize.
It almost feels like "A robot shall not autonomously build or repair another robot" should have been another of Asimov's laws.
I am trying to understand in your view what are the parts that actually breaks and what kind of improvement we would need.
Passing on what I have heard from robotics researchers at lunch conversations.
My impression is that any moving part that is not an electric motor or an hinge breaks.
I'm not holding my breath for advanced robots in the home within the next ten years.
But, then again, I didn't see LLMs coming either.
I have to do it every day too.
So I fully agree with this line of thought... Many a time I have considered that I would happily spend more on a personal 24/7 chef than I ever would on a car. Cars to me are utilities and should simply be efficient and optimized to purpose - food is luxury and taste, it is sublime experience and art. Maybe that's why I can't make it, treating every recipe like a strict command chain isn't how art is done. Can my taste buds be scanned?
But yeah, I think a lot of food is just practicing. And if possible, learn from someone who's food you do really like, and experiment. Just try making some dish you really liked, you'll be surprised at how far you can get.
I saw a cocktail-making robot that was pretty impressive, but it was the size of a room and broke down frequently.
But with robotics, there's no pre-made dataset that can be parroted. Notice that these datasets, e.g. how to fold clothes, need to be created by humans. That's as if humans needed to write algorithms like quicksort to teach LLMs how to code.
Once you lose your job you'll find plenty of time to do all those menial tasks you hate wasting time on.
Jokes aside, programming and mathematics are just well ordered environments. Already digital and verifiable. Perfect for a GPU cluster to power through. The real world is big slow and complex in comparison.
Seeing them play Portal and other video games, I'm curious if they will eventually help solve that last N% of self-driving.
Imagine if someone finds a weird image pattern that gets misinterpreted as instructions and hangs that off a bridge over a freeway.
I'm skeptical, tho. Cost will push for right sizing, much like we have right sized a lot of things about modern cars.
[1] https://waymo.com/blog/2025/12/demonstrably-safe-ai-for-auto...
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 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.
Not to say it was perfect, e.g. sometimes it would get temporarily stuck in a testing loop or it would test scenarios that didn't necessarily seem reasonable. But overall rather effective and capable. This was for a city building game so pre-scripted builds, even if by AI, are likely much easier to create and execute than say playing an ARPG.
Our developers and their agents will never long for a road map the next time they need to build something that touches code across multiple repositories. This is the kind of documentation product that nobody ever had time to build in the olden days. And now, we can get it on a Saturday in about 20 minutes.
What's coming in six months?
You can just paraphrase this prompt:
“Starting with our Helm charts, which you will find in /folder-of-charts, build an interactive website that semantically relates all of the components of our cloud services.”
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.
Recycling then has to be sorted further.
The idea sounds good, but I'm curious about the "low cost" part. How do you account for vandalism and theft? A sidewalk robot seems like an easy target for being damaged, stripped for parts, or simply stolen.
You don't consider the problems. That's how you can pretend it'll be low cost.
There absolutely is minimal wage but is set by local governments, because different places have different cost of living.
There are better protections for work hours for salaried workers than America. Anything above 40 hours get paid at 1.5X and anything above 60 hours get paid at 2x.
And talking about absurd work hours, SK and Japan aren't better than China.
On paper, no. Japan has overtime bonuses too, but you're culturally discouraged from reporting overtime. So 12 hour days are common with no OT. And thats not including "optional" after work outings.
Yet, it's also not uncommon for Japan to bring about the "appearance" of working more than really working. Whether you judge that appearance of work as more or less stressful than China's work standards is a more personal question.
Either way, my main comparison was Asia to the US rather than countries within Asia. US has higher salaries, better minumum wage (but still nowhere near good), and usually better hours. But stability without unions is non-existent as we've seen the past decades.
TLDR; not really trash in the streets anywhere by any reasonable measurement and nowhere near 'plenty' unless the definition of 'plenty' is 'some, somewhere, sometimes.' & Conversion rates don't matter when discussing minimum wage rates, only the local purchasing power matters.
Here's the longer than anyone might expect who doesn't recognize my posts;
Trash may sometimes appear in a few places, mostly in larger inner cities with significant international populations. In my town, and even in the larger regional metro areas, just about the only places I see actual litter are where tour buses full of international tourists deposit daily crowds or where a high speed road passes through forested areas without much concurrent traffic and so people feel that it is acceptable to toss drink bottles and food wrappers out the window unseen. The rest is remarkable for the general lack of any trash on the streets.
It is a common sight in almost every town and city, early in the mornings, to see any number of people actively sweeping the sidewalk AND street in front of homes or businesses. Some will be washing with a brush and clean water.
For nearly the entire country, trash is collected from a designated bird and vermin proof cage or box from every block on most weekdays, on a weekly and monthly rotating schedule, sorted into recyclables: with different days for plastics, paper, small metal, appliances and fabrics, and actual 'trash' which is restricted to burnable foodscraps/paper products which are too soiled for recycling and which do not contain glossy or metallic dyes.
If the pickup schedule is inconvenient at your house, or if your volume of recyclables isn't worth spending 35jpy for a clear rash bag [which is how they manage funding the collection: through region specific trash bags of are clear plastic with color coding for which type of waste belongs in them that you may purchase at nearly any grocery or convenience store] there are sorted recycling bins near the main doors of every grocery and convenience store - just drop off on your way in for shopping.
My wife and I do frequently collect and recycle litter from two areas, because one of them is the walking gardens around a shrine which we wish to see remain mostly free of cigarette butts, and the other is a roadside forest of beech, black walnut and chestnut trees. We visit there regularly, collecting for some extra variety in our diet the nuts, sansai (wild greens) and edible fungi that grow in the forest. Collecting the trash haul is no small part of our biweekly free time in the late summer and fall.
Over this last year, as we have continued working along both sides of a 3km stretch of trees it is remarkable how little new trash is occurring. This seems to match our initial observation that the volume of rubbish was of varying ages and had accumulated over a significant length of time since the last cleanup of this nominally 'public domain' patch of forest. [It is a local land trust with the responsibility of fire prevention and otherwise is a Satoyama designated resource for exactly this kind of community wilderness light impact harvesting - which is why there isn't a designated trash cleanup scheduled but once every 4 to 5 years]
Otherwise the amount of 'trash in the streets' is very much limited to inner city and is one of the reasons underlying growing popularity of tightening of immigration regulations. Not saying it doesn't happen in smaller cities, but rather most of Japan generally engages in cleaning up as soon as they notice any trash. The total of loose trash is remarkably lower than anywhere else I have been, and we do travel to other places fairly regularly; including Taiwan, Thailand, Malaysia in the last few months. None of the clean corners of those places is ...
Starship alone seems to have running operations also in UK, Sweden, Estonia and Czhecia.
Alternatively they could add a chain gun to the robot to deal with the vandals
I suppose it shall be the case for the short term at least that we must admit that “humans” really cause harm. Though perhaps that’s over specific and I should recognize that most crime is committed by eukaryotes.
And it will of course be true to some extent.
I doubt wealthy HOA communities have much random trash to pick up in the first place
But yes, it does also help that a richer community correlates with more care about littering to begin with.
Btw, Singapore shows that we already have proven, low cost techniques for keeping cities clean without robots.
There is no reason to ever have a humanoid, except to make humans feel warm and fuzzy.
I think it's important that someone point out this isn't a 'PR problem'. It's a practical resistance to commodified surveillance. All these domestic robotics companies train on video of users homes, many sell such data, each and every one are a vector for state domestic state surveillance. Not to mention criminal hackers, stalkers and others with an interest in who is at home when and what precisely they are doing. Short of having non-internet connected, locally processing domestic robots - something unlikely to exist in the foreseeable future - they are a privacy nightmare. Bad as google home, alexa and such devices are for privacy - a walking, controllable, camera and set of mechanical arms running loose in a home is infinitely worse.
And PR is the problem you have to overcome for people to let smart devices into their homes too. For instance, people started avoiding Ring cameras once it got out that they're a privacy nightmare -- that's PR. Sure, the people that avoid them care about privacy -- that's why they're listening -- but PR is the reason they even had anything to listen to. Likewise, PR is how people get creeped out by robots scanning their homes. They never wanted that, of course, but they weren't creeped out until they learned about it. That's PR. Now people are wary to let any new devices into their homes, especially robots, because of historical PR like this. And so now it is a PR problem to get people to give you a chance in the first place.
I never said focus directly on downstream. I thought it would be obvious that I'm talking about why you bother with upstream, because the downstream effects are important.
Clearly I phrased something very wrong because it looks like everybody is assuming I'm saying that you should do as much bad as you can possibly prevent people from noticing.
That is pretty far down the list. For the most part, they just want to see what products you have so they can sell you more.
The practical problems with robots are effectiveness, cost and safety in roughly equal parts.
It's very obvious that there is a difference between a single person that you can personally vet, and something that records videos that can be shared anywhere.
> I think internet people care about some theoretical surveillance angle more then anyone else actually does.
Yes, that's usually the case. However in the very current time of surveillance resistance with the de-Flock movement, I think there is increased mainstream awareness of the issue.
Take the recent anti-Flock actions - it’s probably mostly not ‘internet people’ going for evening walks with their angle grinders. Everyone starts to care about privacy when it really becomes invasive.
Likewise, people might be fine getting their elderly parents a robot to help out with household tasks, until intimate stolen videos start appearing on realgrannies.com or similar.
I don't think it's enough to pinky-promise that you aren't sending a dragnet of video with facial capture etc back to the mothership, I think you really end up wanting auditable proof that nothing sensitive can leave the robot or at the very least a no-logging hot-path inference loop (e.g. apple's confidential compute).
And I disagree with you. I'm pretty sure parents worldwide would love a clean-up robot. You can avoid a lot of the risks by making it work only for empty rooms, which is OK because you need to clean up and let the vacuum robot run anyway (when the kids are away sleeping in their bedroom). There's been multiple attempts at building DYI robots to vacuum LEGO bricks off the floor. (Because stepping on them at night is such an immediate pain point.) Unless your product is soaked in hostile behavior and surveillance tech, parents will probably be happy to buy an in-home cleaning robot, no PR needed.
I think the main issue here is that parents are typically busy, which makes them bad startup founders, which is why they cannot "scratch their itch" and turn it into a business.
=> home cleaning robots do not exist because western VCs don't like it and parents aren't usually startup founders.
Places that will leave alone an unsupervised robot don't have lots of trash around.
Entirely disjoint sets.
Or are you suggesting that common people are littering vandals?
Yes. Well, middle class less than working class at least. And only on average. Also individual behaviour isn't the only factor - they also tend to live in wealthier less dense areas, where councils have more money to spend on keeping things tidy, and there are also people who do volunteer litter picking.
> Are you suggesting that wealthy people can not be vandals?
Obviously not.
> Or are you suggesting that common people are littering vandals?
Not even sure what you're trying to say here. You think I was suggesting that all lower class people are littering vandals? Lol.
challenges:
articulated robots are expensive (many would steal them) dust and water resistance with moving parts
good fucking job everyone, congrats.
Let me be frank;
Astra has been UTTER SHIT not just a little, a lot.
It is much more expensive than Sol 5.6 Medium / High and did nothing but write unit tests and write frankly junk code examples:
- In two instances had the direction of the servos wrong.
- Calculated the maximum extent of the gripper wrong, and the closure, so it didn't grip.
- Failed to take into account the gripper requires torque when lifting a pair of socks.
- Failed to actually start testing more than opening and closing the gripper.
- Failed quite spectacularly to calculate camera gimbal extent range correctly, the code was useless.
The test environment has both an onboard ultrasonic for distance, a camera, and a bird eyes view camera while training (only while training).
I've gone back to Sol 5.6 medium/high for the training, it's cheaper and now I'm back to fine tuning, after it had to redo large chunk of the driving code and prevent unnecessary hard stop code kicking in based on the wrong profiling.
It's cost me around 1000 credits, burnt in around 2 hours, looking at video, and photos, and writing bad code. I've also burnt through Regular Plus 5 hour quota in about 30-45 minutes.
Really weird model. No idea how it did so well on all the benchmarks.
It debuted as ~same score as Sol on Artificial Analysis. People couldn't accept it so they had to change the formula.
The model is a big step forward only in desktop use and 3D. I really wanted Astra to be great, but for software engineering, Fable is still on a league of its own.
Even for an absolute robotics newbie such as myself, the article was interesting to read, and easy to understand. Plus it was straight to the point, with no unnecessary waffle.
Just a pleasure all round. Well done Robocurve.
Code as policy is a bad interface in my opinion, but VLM planning has promise. This has been tried in 2022 https://say-can.github.io/, and recently reformulated in https://lianegalanti.github.io/Pigey/
Thing is even recent Gemini Robotics 2 argues for architecture that has a VLM planner and then a VLA/WAM controller + a local small VLA model when connection disappears. And recent SOTA architectures rely on hierarchical design. I think this might be a sensible way to go about it. If you were to train GPT-X on robotics data and to output actions, congratulations! you've just made a VLA. It is enticing for people to just wish for one architecture to do it all, which is why we get stuff like this. I think there is a lot more to gain from modularity and we should not be afraid of specialization.
It's a complete miracle that anyone can have any job today.
So: "how is anyone going to afford robots if no one can work?" Well, exactly the same way as today.
Genuinely.
It's trying to rob people of opportunity to ever migrate and or seek a better life? not just between countries which will very obviously be restricted if actual AGI is ever achieved. Why would you ever give the chance for anyone to come to your country if you do not need their skillset? It would also prevent rural people/town people from going to the big cities.
The obvious end goal is to create a bunch of different "permanent" classes or at least they hope so, I think however you can expect a ton of violence to come from this and people will wish they never invested the resources into this, something beyond what the french revolution ever was, I'm not saying I think it should happen or not, I'm just pointing out the obvious outcome of robbing people of value/worth/dreams in their life.