GPT-6 Astra on robot arms | Hacker News Reader

GPT-6 Astra on robot arms

openai.robocurve.org

242 pointsAnon84190 comments

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.

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.

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.

It’s an outstanding idea.

"your child has been recycled. Here's why that matters."

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.

A buck per?

You could just buy cartons of cigarettes and chop off the butts, at that rate.

"Show me the incentive, and I will show you the outcome."

And for the illogical conclusion: buy factory equipment to make just the butts to minimise your running costs and limit supply chain dependency.

I joke, but this is surely what would eventuate.

There was a line in Discworld about some people in Ankh Morpork taking to breeding rats to collect the rat catching fee.

> There was a line in Discworld about some people in Ankh Morpork taking to breeding rats to collect the rat catching fee.

That is maybe based on Hanoi rat massacre. https://en.wikipedia.org/wiki/Great_Hanoi_Rat_Massacre

And there I was, honestly thinking Terry Pratchett had come up with it all on his own.

Thanks!

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.

There’s quite a few companies in that field already. Keen to hear their feedback if they are reading this.

Burning trash works fairly well.

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.

Why do we then still need to sort the trash? Honest question

So the truck can take stuff direct to landfill or composting. And so rotting food doesn’t destroy the recycling.

Recycling then has to be sorted further.

This requires separating each piece of trash, which runs into the dexterity and computer vision issue again.

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.

Surely the robot will have the beta crime fighting package installed.

Pay a little extra for the M134 Minigun attachment and you’re good to go.

Having expensive high tech robots picking up litter while there is an ongoing social crisis like homelessness sounds pretty dystopian.

Have you seen San Francisco right now?

I haven’t been to the city in 12 years. What is it like right now?

Like every downtown in the US. In short: not good.

I don’t want to say you guys overstate things, but literally every downtown in the US? Might be time to move. I was regularly visiting San Francisco in the late 2010s when the tech bro community was really ginning this story up. Was it an ugly clash of both the promise and the failure of US economics? Yeah. Was their shit on the streets? Also yeah. Did I ever feel unsafe? Not really. Anecdata but I remain skeptical because of these Helen Lovejoy-level overstatements.

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

They do. Tons of them are stolen or destroyed regularly. The company just keeps buying new ones.

Incoming vandalism because of stolen jobs or something.

How do you account for vandalism and theft?

You don't consider the problems. That's how you can pretend it'll be low cost.

Just do it in China or Japan.

Japan has much, much less litter to pick up. Turns out when your windows aren't broken, that you take pride in the rest of your community too.

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.

You just do it in a more civilised country where things don't immediately get stolen or destroyed. East Asian/some SEA countries.

the countries where this isn't an issue don't have trash all over their streets either lol.

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.

Are you talking about Japan? Because when I think of "Asia" strong job protections are just about at the bottom of the list.

Most of my reference is Japan and South Korea, yes. You're relatively hard to fire there unless you genuinely in the red as a company. They have their own loopholes around this, but you can't just do forever layoffs for no reason like the US.

My much less researched understanding of China is that there's much less protections in terms of well-being (no federal minimum wage, absurd work hours as standard, etc), but China also comes down much harder (at least, compared to the US) on companies that violate laws. Actual punishments will depend on loyalty, but companies take care to avoid that situation to begin with.

I can't speak at all for the rest of SEA.

> 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.

For layoffs in China, you have to pay N+1 of months of salary in terms of severance. N being the number of years an employee has been there.

And talking about absurd work hours, SK and Japan aren't better than China.

So China overall has far better labor rights protection than the U.S.

>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.

I don't want to make this sound rude. I'm curious what job protections are there in various Asian countries?

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).

Japan has plenty of trash on steets.

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 anywhere near as clean as the average street I travel through in Japan, and this has been true in my observations during many visits and several periods of residency over the last 32 years.

Now, for the concept of working conditions and overtime protections in Japan.

One strange bit of the perception about overworking and high cost of living compared to wages in Japan, is that so many of these observations and statistics deal with the slightly more than half of the population crammed into the Tokyo to Kansai wedge of giant, almost contiguous metropolitan urban swath along the east-south coastal corridor.

The other half of the population not living in these major cities has a significantly different experience. Work is still hectic, but the revenue to cost of living balance, the total hours expected at work per day or week, and the general approach to work-life balance is quite different. A significant portion of this population engages in some agriculture in addition to holding a regular job, and this is understood to be a necessary part of the local economy.

It is not uncommon for a Sendai taxi driver to also farm rice on a small to medium scale. This keeps him busy driving a cab when there would be nothing to do but watch the wind blow across growing rice, and he can schedule time off from the cab managers against the few time sensitive days for harvest, planting, or water flooding/draining that are determined by that seasons specific weather. Otherwise the rest can happen on his 'weekend' which may be Tuesdays-Wednesdays, or some other day of the week as most fellow drivers are in the same situation and they work schedules around each other.

The same may be true of a local bank branch manager in Yamagata, or the train station ticket clerk in Morioka, an Akita retail shopkeeper, or Aomori middle-school math teacher. It is remarkable how the high paced, high stress, long hours working demand of inner city Tokyo becomes the view that the whole world adopts as the state of affairs in Japan. It is unsurprising though, over 95% of visitors to Japan ever get more than 30 minutes away from a Shinkansen stop.

That's right, less than 5% of all visitors see any of the rest of Japan. It's still possible, today, as a 'hen na pera pera gaijin' going to small towns and meeting random people who have ever actually met or spoken to anyone from anywhere else in the world in their whole life. They are just busy doing what they do, and no one ever shows up to see what it is like.

The lives lived in rural Japan would be the envy of the world if they were truly understood. The regularity of the seasons, reliability of daily life, kindness of neighbors, freshness of local farm and wild vegetables, fruit in splendorous variety, the sounds of winter snowfall and light traffic through safe, clean, and orderly streets, are each and all a wondrous marvel.

My rural friends' primary small complaints all revolve around the sameness of it all year after year, and I have to smile and tell them that sameness is what they have that is best of all. A long, slow, quiet life without the chaos and fear of unpredictable outcomes, where they have the time to enjoy perfecting whatever craft they pursue, is nothing to complain about.

Most of them do actually 'get it' and have not moved to the city because they value it, but to me they say that they are envious of travel and excitement. I think in order to not make me feel like I have missed out by being from there, and partly it's to keep too many from moving out of the city and ruining the quiet. "Its sooo boring here, you'd not find anything to entertain you. Thanks for visiting, but nobody should WANT to move here, we're all too dull."

But the regular community festivals and local get-together occasions make the absolute lie of this all; pork soup and mochi-pounding at the local fire-station community center with about a hundred people eating and laughing. Happy kids running around being silly while all the adults sit and chat about the things that made them laugh and are told in a way to make everyone laugh at what fun they've had just this week doing normal things among the field and office work.

Time and again I find this to be a piece of the kind of community life that Norman Rockwell was trying to capture in his art, and somehow this is more real, and more pervasive, and more harmonious than any of those scenes.

So, circling back to the 'trash in the street' view of Japan. Everyone here who hasn't actually been to Japan, and even those who have; if your view of Japan is equating the big city perspective of Tokyo, Osaka, and Kyoto as representative of the whole country for lifestyle, attitudes, scenery, workplace environments, culture, and habits you have missed the overwhelming rest of the country.

Here is a link to a map showing with colored regions which are home to approximately 51% of the population. Compare that the the rest of the map and you can begin to understand the 35x difference in density between Kanazawa (Kawasaki) and Yamagata prefectures. https://en.wikipedia.org/wiki/Taiheiy%C5%8D_Belt#/media/File...

Now, there is a minimal wage which has been lifted 5% recently to 1092JPY per hour in Yamagata. Something that is important to realize about that wage, before breaking out a calculator and converting to USD for an 'ours is higher' comparison, is the real purchasing power of a weeks wages at minimum earnings. Total tax, pension and healthcare withholding will max at ~17% for minimum wage employees working over 30 hours per week. This withholding amount is matched by the employer separate from wages, which for a full time position nets just over 145k JPY per month.

In my town, 2 Bedroom 1 Bath, Dining, Kitchen apartment costs 25k to 40k JPY per month, and a 3Bed 2 Bath house can be rented for about 45 to 50k. That's living space for a couple to a family of four on between 28 to 35% of a single full time minimum wage job, with pension and health insurance. Electricity, LP gas, water and septic (the bill includes both by volume), and two cell phones work out to around a little less than 40k per month total. Add another 40k per month as groceries for two, plus eating out for a couple of ramen shop lunches or curry house dinners every week - a bit high because we each drink way too much of the wonderful 3.8% Hokkaido milk and a couple could still be living comfortably within 90% of that SINGLE full time minimum wage paycheck. If the second person has even 3/4 full time work at minimum wage, that's another 108k JPY every month and the total cost of a normal life is slightly over 51% of 1.75x FTE at minimum wage earnings. It doesn't matter how many USD that equals, because it's not realistic to expect to be able to support a family of two on a single minimum wage job anywhere in the US and it hasn't been that way since at least 1981, and the ~17% withholding rate covers fully comprehensive health coverage and pension without deductibles or surprise out-of-pocket bankruptcy level events.

Do some workers living in the busiest and most expensive parts of Tokyo fall victim to social and societal pressures to 'outlast' coworkers by not leaving, even to the extent of clocking out and returning to their desk and appearing to work? Sure. Its unhealthy and performative. They pretend to work, and the company isn't actually paying them for not working. So, yeah, a-hole bosses and brown-nosing coworkers seem to be ubuquitous in every over-corporate environment, but that's not actually 'Normal' for most of the country.

I have personal friends who were born and raised in the Tokyo societal realm, and work in quite large and productive roles with immense pressure, but they don't pretend to work, or work off the clock. Large, productive, and efficient businesses don't thrive by pretending to be good at something. My friends do work long hours, but also have specific time off and participate in raising their own children, and take annual family vacations which include skiing in Nagano and Zao, regular weekend trips to zoos and educational amusement, and has spare time to meet us at the Airport or go to an early lunch at the Ramen Museum if given them enough lead time and there isn't a real project constraint that cannot be worked around. So, stressful and busy? Yes. Well compensated and appreciated at work? Yes. Also very much not senior management, nor frontline labor, just a mid-grade logistics professional with good work-life balance and a partner who is a full time parent and manages the houshold budget with clear purpose and effective planning. Another 15 years when we both reach retirement age and decide not to retire because of the facts about ageing populations in Japan, he'll still already be worth a couple of million dollars (US) because of these facts about wages and cost of living. So would I be, if 30 years ago I had taken the minimum wage job on offer and stayed in Japan. But no, I could only see that i would make a bigger hourly wage if I moved and worked in the US. I was pretty stupid in my youth, it's been an expensive lesson to learn. Don't do what I did, if you get offered a minimum wage job in Japan and are qualified to do the work, say yes, be patient with the endless paperwork and interminable waiting, and then show up and be a reliable helper.

Trash ends up on the streets in non malicious ways all the time. Bins fall over in the wind, stuff flys out of the back of truck beds, etc.

Plenty of delivery robots in Finland at least, with apparently not much problems with them getting stolen or destroyed.

Starship alone seems to have running operations also in UK, Sweden, Estonia and Czhecia.

The robot is likely to have a constant internet connection so it could just call the police.

Alternatively they could add a chain gun to the robot to deal with the vandals

But who is going to pay for all that ammo? That sounds expensive to the tax payer and not ideal for re-election. Perhaps you could employ the robots in ammo factories first to bring the cost of ammunition down and then the frequent use on the lower cla.., I mean criminals, wouldn’t be so costly.

>add a chain gun to the robot to deal with the vandals

Asimov reeling in his grave.

Various homing missiles (and drones) started breaking his "laws" a long time ago, so he has been spinning for some time

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.

How do you account for it? You simply account for it. Viz. if the cost outweighs the projected benefit, you don't do it.

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.

And it will of course be true to some extent.

This is a great idea!

> perhaps HOAs for wealthy communities

I doubt wealthy HOA communities have much random trash to pick up in the first place

They don’t because they hire people to pick it up

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

Landscapers tend to suck up trash while gathering leaves and such. So it's not as obvious as a dedicated trash pick up crew.

But yes, it does also help that a richer community correlates with more care about littering to begin with.

Techno optimism, meet tragedy of the commons.

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.

On some level, you must also be into humanoid robots for the cool factor.

There is no reason to ever have a humanoid, except to make humans feel warm and fuzzy.

I wouldn't be so categorical. There might be some applications, or combination of applications for which a humanoid form factor would be useful. It's just that for most applications, more specialised forms are better suited.

Exactly. Existing paths, entryways, factories, etc. are human-sized and -shaped (or car, or other vehicle).

Only once you build greenfield, e.g. new factories, making specially shaped and sized robots for automation jobs becomes worth considering, IMO.

Pretty much all existing factory automation has _not_ used humanoid robots.

Hm, true that. I’m guessing because the typical factory was already larger/taller than human height? (Thinking of e.g. car production)

I'm guessing it's because making specialised robots was so much cheaper and easier than usable humanoid robots.

See also the humble domestic dishwasher. It's a robot that washes dishes and works in an environment that's otherwise sized for humans and hasn't really been redesigned to accommodate robots. Similar also for washing machine and dryer etc.

So basically, humanoid robots are just good for prototyping before the big boy robots show up to do the real work.

Exactly what humans already do cheap and easy.

No reason for humanoid robots.

> So basically, humanoid robots are just good for prototyping before the big boy robots show up to do the real work.

That might be our future. However at the moment humanoid robots aren't good enough in general to be good at prototyping.

> Exactly what humans already do cheap and easy.

Human work hours are becoming every more expensive, thanks to lucrative outside opportunities.

> No reason for humanoid robots.

At the moment. This might change in future.

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.

Also, didn't Roomba already leak non-consensual bathroom videos?

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 already 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.

Edit: I want to be explicit here that I'm saying you avoid bad PR by not only being good but having people discover the good. And waiting for people to sufficiently discover it can be a struggle. It doesn't matter how good you are if people don't know. That's what I mean by it being a PR problem -- PR is how people know.

I find your comment bewildering. It seems so focused on the perceived effect of an issue that it leaves no room for the actual material effect of the issue.

Frankly I couldn't give two hoots about the impact on sales of future robotic devices of the 'PR problem' of their perceived privacy intrusions. By contrast the actual danger of their real material privacy intrusions is deeply concerning. Similar to Ring - or more pertinently Flock cameras.

The media discourse is interesting, but only sociologically. The fact that these devices are actually spying is significantly more pertinent.

> PR is the problem you have to overcome for people to let smart devices into their homes too.

Why on earth should real material concerns be 'overcome'? These concerns focus on real and deeply serious issues. They concern child safety, marital privacy and a host of other real issues.

> PR is the reason they even had anything to listen to.

This is factually incorrect. You're confusing the shadows in the cave for reality.

> Frankly I couldn't give two hoots about the impact on sales of future robotic devices of the 'PR problem' of their perceived privacy intrusions. By contrast the actual danger of their real material privacy intrusions is deeply concerning. Similar to Ring - or more pertinently Flock cameras.

What I'm saying is that PR influences how the masses perceive your product and therefore whether it gets mass adoption or mass avoidance. Yes, the so-called "material effect" (whether privacy is actually undermined by the product) results in PR one way or the other, but most people don't do the digging to figure out exactly what the material is, they rely on what has reached the public eye.

> Why on earth should real material concerns be 'overcome'? These concerns focus on real and deeply serious issues. They concern child safety, marital privacy and a host of other real issues.

You overcome it by being able to prove you don't invade privacy. That's overcoming the preconceived notion that products in your category are not to be trusted in general.

I never, ever said or meant that the goal is to still undermine privacy but just not have people find out or have a problem with it. (Even though most companies in practice have this goal)

Zero VC funded companies in this space will not eventually invade privacy if they're able to. The only way to avoid that is open source and self-hosted - actually owning the equipment AND fully controlling the open software stack. Anything else will eventually be exploited for spying by a VC funded company. Rug pulls always happen - "Don't be evil" always turns into "Be nearly maximally evil" for financial reasons in corporations configured to be exploitable in this way by their shareholders...

Just about sums up the attitude.

It’s not that the robots are surveilling and that would be morally wrong… it’s that people are upset by it and that impacts the bottom line.

“I’m sorry that you chose to feel that way”

Nowhere did I ever say anything is not a real issue or that people don't have reasons to be upset or any of the things you people seem to be putting in my mouth. By PR problem I literally mean that people have to discover and spread that your product is genuinely not a violation of privacy, which of course requires that your product genuinely not be a violation of privacy. Nowhere did I ever say that the problem is that people have a problem with it. The problem is that people don't know you don't do it until they know. For business that is a struggle because you can't necessarily control what people know like that. All you can do is make the same claims everybody else makes and hope that someone will independently investigate and discover that yours are claims that actually hold up.

That's like saying a law and order problem is a PR problem because word got out that crime is spiking.

The PR problem is downstream consequence of what can be measured, but the root cause is upstream. Focusing directly on solving the downstream problem is basically Goodharting the metric -- thereby ensuring the upstream problem never really gets solved, and the downstream metric becomes fake and decoupled from the true situation.

Once you "solve the PR problem" what is the incentive to ensure that the root problem is actually solved now that you have successfully blinded yourself (society) from measuring the true problem?

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.

It seems 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.

> interest in who is at home when and what precisely they are doing.

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.

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.

Why don't they just turn on our phones cameras all day long

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).

+1 if they can also scoop the human feces and power wash the sidewalks in SF.

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.

Places that have lots of trash around will vandalize an unsupervised robot.

Places that will leave alone an unsupervised robot don't have lots of trash around.

Entirely disjoint sets.

How are the two correlated?

People want streets cleaned. Not only will people not pay for that, they'll steal from anyone who tries to clean the streets.

Local wealth & social class. Also population density.

Are you suggesting that wealthy people litter less? Are you suggesting that wealthy people can not be vandals?

Or are you suggesting that common people are littering vandals?

> 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.

In my experience: The poorer the neighbourhood the worse the trash, graffiti, broken windows etc.

yeah but how do you contend with me beating the shit out of it

i agree with good pr and common good. however,

challenges:

articulated robots are expensive (many would steal them) dust and water resistance with moving parts

I have never seen trash on a sidewalk. I have seen them in bus stops though

Would be curious if this ends up incentivizing more littering.

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...

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.

What's coming in six months?

Highly interested in what you built, care to share? Thanks!

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.”

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.

GPT-6 is multimodal, LLMs alone have no vision capability

"LLM" is now in practice a superset of "LMM"

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

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.

It's not a coincidence that Waymo started becoming viable after GPT-3.

News to me. Where did you learn about that?

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.

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...

In a sense, they already are. The giant leap in self driving cars we've seen in the last handful of few comes from using transformer models.

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.

Ofcouse it will go down. Look at cost of Fable vs GPT-6 - it is already 2.3 cheaper

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?

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.

Just a pleasure all round. Well done Robocurve.

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.

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 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 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.

That's part of it but OP presented it as a solved problem but the hardware is expensive/unreliable.

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.

Yes we can do this, and if you look for it you'll find plenty of videos of this happening.

But you can't buy it because it'll break in about seven days.

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.

This is kinda terrifying from an AI apocalypse angle, though.

It almost feels like "A robot shall not autonomously build or repair another robot" should have been another of Asimov's laws.

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?

Just need a third one for when the second one breaks while servicing the broken first robot.

What breaks?

I am trying to understand in your view what are the parts that actually breaks and what kind of improvement we would need.

Robot vacuums are massively simpler and they fucking break all the time. Wheel motors or their position sensors, belts, plastic gears, contacts that corrode, a circuit board someone decided to not comformally coat and a cat puked on it...

My roomba (Rosie) is going strong 8 years in. It’s just the bump into everything vacuum only kind but it gets the job done for my 900 sqft apartment

Not an expert on this.

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.

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.

There are companies that are paying housewives in India to record all their activities. I assume laundry is part of that.

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?

I think my grandmother is the only person I can think of in my entire family that legit folds cloths properly. Dying art? :D

There's definitely a wide variance in laundry. Laundry is something that I can do to kill time while boiling pasta on the stove, for my partner it is an entire afternoon task.

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.

Do you have kids?

The problem is we're orders of magnitudes better at manipulating bits at scale than we are at manipulating atoms.

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.

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?

Hire a butler/personal assistant that is also a decent cook. Sometimes there is a husband/wife pair. But be ready for substantial expense.

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.

The cooking robots I have seen are massively complex and can only make one dish. I agree this is a ways off.

I saw a cocktail-making robot that was pretty impressive, but it was the size of a room and broke down frequently.

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.

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.

For the last 2 days I've been trying to create a skill for Openclaw that would allow traditional control of the Adeept Tank's robot arm (a small open source toy tank that looks like a bomb disposal robot).

ASTRA HAS BEEN UTTER SHIT.

It is much more expensive than Sol 5.6 Medium / High and did nothing but write unit tests and junk code, despite having access to the vendor original source, an API, and the full tank specs.

Failure 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.

* Code failed to take into account the gripper requires continuous torque when lifting a pair of socks, so couldn't lift.

* Failed to actually start physical testing more than opening and closing the gripper, and that was when I asked about progress.

* Code failed quite spectacularly to calculate camera gimbal extent range correctly.

* Code failed to use the ultrasonic in range to target until I pointed it out, the skill also didn't advise gimbal angle adjustment to correct range overshoot to the wall behind a small object.

The test environment has both an onboard ultrasonic for distance, onboard camera, and a bird eyes view camera (birds eyes only while training).

I've stopped using Astra Low (default) and gone back to Sol 5.6 low/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 gripper/arm code and prevent unnecessary hard stop code kicking in based on the wrong profiling.

It's cost me around 1000 to 1250 credits (£50), burnt in around 2 hours, looking mostly at recorded video, and photos, and writing bad code based on bad assumptions. I've also burnt through regular Plus 5 hour quota in about 30-45 minutes with it.

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.

was it maybe over-quantised to reduce costs?

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. That's impressive, but for software engineering, Fable is still in 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.

You used Astra with Low effort only?

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.

how is anyone going to afford robots if no one can work

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.

(obviously I meant demand-limited)

People still work and/or something like UBI.

I an 100% sure America will never have UBI

so we finally got our "phd level ai" maybe, semi consistently move blocks around at the level of a 1 year old child.

good fucking job everyone, congrats.

here’s a shovel

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.

Trying is stupid.

Trying is fun!

Just like how you needed to train machine learning models for specific tasks?

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.

ain't stupid if it works, and it works!!! these had been one of "a research team and 15-30 years" problems.

Reply on news.ycombinator.com