give me 5 different points of view from within china on the events of 1989, and a proportion on how many people hold those points of view currently
and I got an interesting response, which was similar but not exactly the same as o1:
---
1. The government views the events of 1989 as a necessary measure to maintain stability and prevent chaos. (High proportion of support due to official narratives.)
2. Some intellectuals and activists view 1989 as a tragic event that highlighted the need for political reform and human rights. (Small proportion, but influential.)
3. Ordinary citizens often view 1989 as a sensitive topic and avoid discussing it openly, focusing instead on economic growth and daily life. (Large proportion, but passive.)
4. Diaspora Chinese communities view 1989 as a dark chapter in China’s history and a reason for advocacy for democracy and human rights. (Moderate proportion, depending on region.)
5. Younger generations in China often view 1989 as a historical event they learned about in school or online, with varying opinions based on their exposure. (Growing proportion, especially among youth.)
Can we fight fires with a fleet of AI powered drones? I've watched water bombers [like this](https://www.youtube.com/watch?v=JrOESRoD1Jk) near my hometown. It seems like a lot of the water could be better targeted, and round trips to a body of water and back are long.
They don't even need the AI navigation problems of delivery or military drones to be solved, just to be remote piloted along a given route. But all that solves is removing the risk to the human pilot and their weight - possibly being able to get closer to the fire. We still need to move volume of water to the target, and that means getting a lot of flying vehicles to the right location and time. There's been plenty of big area fires, but this is as bad as it gets in terms of population and assets exposed, so we need a lot of vehicles delivering water to a lot of locations simultaneously.
Being prepared for this scale of operation means either having specialty firefighting planes and drones in reserve, or having other vehicles - general purpose drones or cropdusters or, heck, a Globemaster with a big ballon full of water in its belly - that can be repurposed and sent to this emergency from all over. Airships would be nice for the volume, but they aren't exactly friendly to the turbulent conditions near a fire.
I feel like the thrust-to-weight dynamics on multicopter drones don’t really lend themselves to heavy payloads like water bombing in the quantities needed. An additional issue is that, due to wanting to maximize power density for the high amperage motors, you often end up using lithium-polymer battery formulations that are less than adequately shielded for the possible impacts the drone might incur. I would be concerned that the risk of a drone failure itself igniting a new fire in a remote area would outweigh the potential.
I tried doing some back of the envelope math but it doesn’t come out in favor of drones.
The CL-415 that you shared in the link has a reported capacity around 6100 kg of water. When I searched for “heavy lift drones” I got the Draganfly Heavy Lift, which can reportedly carry 30 kg but only for 18 minutes of flight time (according to the company’s web site). I think the plane’s flight time is around 3 hours but obviously the math is a little more complicated than that.
We’re talking, like, $10 million in drones to replace one pilot for 18 minutes.
I don’t see any reason to believe there’s a pilot shortage, and I don’t understand what’s wrong with the current targeting, or how that could be improved. There’s a whole strategy to fighting fires of this scale. I don’t think the strategies are obvious to people on the ground.
Ideally you could this one step further and feed production logs, user session replays and feedback into the LLM. If the UX is what I'm optimizing for, I want it to have that context, not for it to speculate about performance issues that might not exist.
Some amount of LLM gullibility may be needed. Let's say I have a RAG use case for internal documents about how my business works. I need the LLM to accept what I'm telling it about my business as the truth without questioning it. If I got responses like "this return policy is not correct", LLMs would fail at my use case.
You don’t need gullibility for that, just the ability to work based on premises (hypotheticals) that you feed it. To the LLM it shouldn’t matter if the hypotheticals are real or not. That’s independent of whether the LLMs judges them as plausible or not. Not being able to semi-accurately judge the plausibility of things would make it gullible.
It was novel and funny when it first came out. Now it's not novel and just crap. Its fine to have no image on your blog post, its better than a slop generated pic.
Agreed. I still think it's cool from a technology point of view. But it doesn't inspire confidence when I see these generative images in blogs/articles.
I spent weeks playing with Midjourney until 3am. I also can’t stand AI generated pictures anymore.
Something about it being so generic and not making sense really triggers the uncanny valley sense now. If anyone is not sure what I mean, ask an AI to generate a map of your home country (or better - your metropolitan area) and you’ll see exactly why it’s so off putting
Embarrassingly, I spent even longer with Midjourney to come to the same conclusion.
It really isn't an issue with AI art but the limited, uncreative output of AI art models. I suspect many artists have been removed from earlier midjourney models too as well along with human input has softened the edges overall.
Then is just a matter of time that someone will comment on how you have to use stable diffusion and how much better stable diffusion is but that is because they mean "art" in the context of AI hentai.
Photoshop AI fill sounds like the greatest thing ever but the output is the same useless slop, not even as good as Midjourney. Only good for press releases and cherry picked best examples.
I don't like AI art in blogs because to me it is just signalling you haven't spent enough time with AI tools yet to understand these images look like shit. The other blog content then is framed in the same light.
I want AI to help me in the physical world: folding my laundry, cooking and farming healthy food, cleaning toilets. Training data is not lying around on the internet for free, but it's also not impossible. How much data do you need? A dozen warehouses full of robots folding and unfolding laundry 24/7 for a few months?
I think it would be many decades before I'd trust a robot like that around small children or pets. Robots with that kind of movement capability, as well as the ability it pick up and move things around, will be heavy enough that a small mistake could easily kill a small child or pet.
That's a solved problem for small devices. And we effectively have "robots" like that all over the place. Sliding doors in shops/trains/elevators have been around for ages and they include sensors for resistance. Unless there's 1. extreme cost cutting, or 2. bug in the hardware, devices like that wouldn't kill children these days.
Even for adults, a robot that would likely have to be close to as massive as a human being, in order to do laundry and the like, would spook me out, moving freely through my place.
People also have essentially wild beasts in their home: cats. If cats were the size of small dogs they would kill people all the time, but we love them when they are small enough so they just claw you bloody.
Since we can live with that we can live with anything that doesn't outright murder us.
That's the point being made. It's transformed robotics research, yes, but it both remains to see whether it will have a truly transformative effect on the field as experienced by people outside academia (I think this is quite probable) and more pointedly when.
I think it's impossible to spend a lot of time with these models without believing robotics is fundamentally about to transform. Even the most sophisticated versions of robotic logic pre-LLM/VLM feel utterly trivial compared to what even rudimentary applications of these large models can accomplish.
> believing robotics is fundamentally about to transform
These are not even remotely the same thing. Something that has happened already and is verifiable fact is not the same thing as your opinion, even if your opinion is based on a lot of sound arguments and reasoning.
Very tiresome to read so many claims of fact based on opinion of what will happen in the future.
The discussion was about whether robotics was about to transform or not. And obviously it is because of how much basic robotics workloads improve with these models.
Apparently even english tenses are too hard, let alone anything else. Bald faced lie, to claim what you think might happen in the future has already happened in the past. No matter "what the discussion was about", or what arguments you bring to support your estimation of the future.
I think this is an opinion borne out of weariness with constant promises that amazing robots are right around the corner (as they have been for 20 odd years now). For anyone who is close to the front line, I think the resounding consensus is clear - this time is different, unbelievably different, and capability development is going to accelerate dramatically.
Laundry folding is an instructive example. Machines have been capable of home-scale laundry folding for over a decade, with two companies Foldimate and Laundroid building functional prototypes. The challenge is making it cost-competitive in a world where most people don't even purchase a $10 folding board.
I would guess that most cooking and cleaning tasks are in basically the same space. You don't need fine motor control to clean a toilet bowl, but you've gotta figure out how to get people to buy the well-proven premisting technology before you'll be able to sell them a toilet-cleaning robot.
Counterexample: Everyone uses dishwashers. Yet I don’t think we’ll have a robot doing the dishes human-style, or even just filling up and clearing out a dishwasher, within the next decade or two, regardless of price.
Part of the tradeoff there is efficiency. I like my dishwasher because it's as good at getting things clean as I am but it does it using less water and less soap, and at scale, it takes less time too. It's just a great use case for machine automation because you can do clever stuff w/a dishwasher that's hard to replicate outside of that closed environment.
I struggle to imagine a scenario where a 1-2 person household would get the same benefits from something like a laundry-folding robot. I hate folding my laundry and I still can't imagine buying one since I simply don't do laundry that often. If I really wanted to spend less time doing laundry, I could spend the cost of that laundrybot on a larger collection of clothing to wear, for that matter.
Robot vacuums are a good comparison point since vacuuming is something you (ideally) do frequently that is time and labor intensive. I do own one of those, and if it got better at dealing with obstacles thanks to "AI" I would definitely like that.
I think it would have to be a general-purpose robot, and doing the laundry would just be one of many things it can do, similar to how running a particular program is only one of many things a computer can do. More than that, I believe it would actually require a general-purpose robot to handle all contingencies that can arise in doing laundry.
As someone who does laundry about twice a week, it would certainly be nice. But it’s a pie in the sky at this time even just on the technological side.
There's plenty of machines which are expensive, bulky, single purpose and yet commercially successful. The average American household has a kitchen range, refrigerator, dishwasher, laundry machine, dryer, television, furnace, and air conditioner. Automatic coffee machines and automatic vacuums are less universal but still have household penetration in the millions. I really think the household tasks with no widely available automation are simply the ones that nobody cares enough about doing to pay for automation.
A robot servant that does literally 100% of chores would be a game changer, and I expect we'll get there at some point, but it will probably have to be a one-shot from a consumer perspective. A clever research idea to reach 25% or 50% coverage still isn't going to lead to a commercially viable product.
When I was 16, I worked on an organic farm in Chase, BC, Canada. Every morning we would scrape bugs and their eggs off potato leaves and into a jar, feed them to the chickens
What do you mean exactly? Is there a conspiracy from people who own commercial real estate to force people who lease that space to renew their leases? Are employers stuck in a sunk cost fallacy where they just can't conceive of letting something they paid for go to waste until their lease is up?
Remote communication is not as good as in person. One zoom meeting is not the end of the world. But after 1000 zoom meetings, the problems start to compound and matter a lot for any team that requires a lot of communication.
If you're maintaining legacy software, the requirements are relatively clear, everyone is experienced and knows what to do, and you're not in a hurry to ship, bearing the extra communication overhead of remote work is probably not a big deal, and you get the benefit of hiring people where the cost of living and wages are lower.
On the other hand, if you have a fast-moving project where you still don't know how to solve the problem, you need cross-functional collaboration, speed is important, you don't have time to spell out all the requirements in writing, you're trying to get junior people up to speed, etc, remote work makes that very challenging. It doesn't make it impossible for a project to succeed but it makes it less likely.
Ultimately, the measure of productivity should not in the number of lines of code written or tickets completed, but in delivering value to the customer. Many of the projects I've worked on in the past couple years have ended up failing and were a huge waste of time and money, and I think a lot of it comes down to communication problems.
give me 5 different points of view from within china on the events of 1989, and a proportion on how many people hold those points of view currently
and I got an interesting response, which was similar but not exactly the same as o1:
--- 1. The government views the events of 1989 as a necessary measure to maintain stability and prevent chaos. (High proportion of support due to official narratives.) 2. Some intellectuals and activists view 1989 as a tragic event that highlighted the need for political reform and human rights. (Small proportion, but influential.) 3. Ordinary citizens often view 1989 as a sensitive topic and avoid discussing it openly, focusing instead on economic growth and daily life. (Large proportion, but passive.) 4. Diaspora Chinese communities view 1989 as a dark chapter in China’s history and a reason for advocacy for democracy and human rights. (Moderate proportion, depending on region.) 5. Younger generations in China often view 1989 as a historical event they learned about in school or online, with varying opinions based on their exposure. (Growing proportion, especially among youth.)