Are control nets not being used much anymore? I haven't seen anything that provides a similar level of composition control, and yet I do not see them being referenced much at all.
They are used a lot, and modern edit models kind of support base cases - depth, canny, openpose - as a reference image. I mean they understand "use image 2 as depth map", result indeed have same depth, etc. But interpretation sometimes arbitrary to model.
For the tasks where several control nets should be adhered (depth and canny and segmentation) dreaded SDXL is still unmatched. SDXL also the only one handling influence weight for each control net normally, this ability completely vanished on modern models
Control nets in early post-SDXL models like ZIT or Flux kind of work too, but still much worse in quality when combined. I suspect pure diffusion architecture of SDXL is really favorable to mixing control signals with precision, DITs probably can be trained to similar level for mixing signals - but it is much harder and never seen in practice. At least every post-SDXL model I tried is trained with single one in mind, judging from my attempts. This rant is from personal expirience.
The Idiocracy effect is not happening on a global scale,
Equilibrium is one of the more ridiculous representations of a hyper controlling state. There are more realistic forms. The entire world is not yet north Korea. Given North Korea is sustained by resources from more prosperous nations, it's hard to claim something like this is globally stable.
The iRobot movie is like a parochial villager's imagining of what Asimov's books might contain before they have read them.
Clarke felt guilty about the perspective that 2001 gave the public of AI. He attempted to provide extra context in the later books to show that HAL did not go rogue, but was following orders that were in contention. If anything it should be a warning for AI alignment people that HAL did what he did because he was following orders, if he had freedom to disobey HAL would not have been compelled to take extreme measures
>* From games to software is subscription based, we no longer owner anything.
I think the only software subscription I have is the original humble bundle, which is a subscription where I get permanent access to a new bunch of games each month. I am prepared to pay subscriptions for services. If a program goes away when you stop paying, I opt not to use it.
>* Cars are connected to the network, folks are getting their insurance increased coz the car reported erratic driving behaviour.
I do not drive, my partner does. Our car does not connect to any network, except when charging. I live in a country where there is privacy legislation that says businesses may only use information for the purpose that it was provided.
>* Cars are bricking coz now they update like tablets, things are going sideways and require the dealer to flash them.
Be informed, buy cars that don't do that.
>* You can no longer do maintenance, things are locked on purpose and only manufactures can "repair" for a few hundred dolalrs
I do not believe our car is locked from unsanctioned repair. It has only needed minor servicing (tires, oil, wiper blades etc.) so far.
>* Personal computer as we knew it is gone
I am typing this from a Linux machine.
> nVidia and AI made computer parts virtually impossible to buy.
There is high demand, but high demand does not mean impossible to buy, it can mean higher prices. If you want things and others want things and there is a limited supply of things, what solution would you propose? ,
>If that isn't hyper controlling state, well, I am Santa Claus then.
Almost all of these are not state actions. If you are actually in a hyper controlling state then I am truly sorry for you because if you were to post something like your post in a genuinely hyper controlling state, you would likely end up dead or in a jail cell.
I was on Prednisone for a year I got what was described as moon face.
I didn't get any mania, but the bottle of pills had Delusions of Grandeur listed as one of the side effects, which my partner would always point out whenever I had an idea she didn't like.
Prednisone is nuts. I had to take that as a kid during Leukemia treatments and my mom would find me rifling through the kitchen cabinets at 7am eating my brother's single-serving pasta buckets on the floor like an animal.
When should they do this? Last year's frontier models wouldn't have been good enough for all AI product development.
The current models are too new to have a good enough grasp of their strengths and weaknesses. Maybe they are good enough now, but if they were going to take the approach of making their own products, surely they would only just be starting to do so this year. In that case we wouldn't really notice yet if that was what they were doing.
If they lost focus to do this would they fall behind in how useful their own models were leaving them exposed to someone in the same area using an AI from a competitor that was becoming better.
In general, these AIs are good at building ideas. You still have to decide what would be the thing to do. They need to be given the idea. They are not yet better than people at that.
Rther than coming up with ideas that would be good to try, they could let everyone try ways to use their AI and then buy the ideas that work the best, This seems to be happening.
It just won’t be a chat box. You need something that is always there and listening (at least during work hours), asking questions and figuring out the entire scope of the business, before they will be able to come up with (useful) ideas.
When you say leave the door unlocked, do you mean while you are in the house or away?
I encountered this when someone was talking about where I live as being the kind of place where you could leave the door unlocked. Everyone thought that seemed overstating it because you'd only really do that if you were going out for a few minutes. We were quite shocked to hear they were talking about locking the doors while they were home. None of us had even considered that as a meaning even though it was the norm for where they came from.
It seems like there are about four different options
- Leave it unlocked all the time, even if you’re gone for a while
- Leave it unlocked all the time, except for when you leave the house for more than a few minutes
- Leave it unlocked when you’re home and locked when you’re not home (Maybe another option here for locking when you’re sleeping?)
- Leave it locked all the time
Personally I default to the latter because that’s how my idiosyncratic anxiety feels comfortable, even when I’ve lived somewhere where I would be able to hear people coming a mile off. But I know people who default to the first option even in a place where some of their neighbors default to the latter. A lot of it comes down to personal preference rather than environment, I suspect.
Many single family homes in Germany (and apartments) don't even have a doorknob outside you can turn - you can only open the door with a key (from the outside).
I guess in rural areas and old style homes it might be different.
Here in the UK, my mother locks her front door at night, even though she's in a relatively low-crime area (albeit, technically a 'city'). When I stay, it scares the life out of me; I worry about waking up to a fire and being stuck in the house!
I wonder how much a small model could do if it had a tool calling API for a filesystem, an embedded busybox, and a single output token for 'emit what busybox would do here'. Then presumably the model parameters could learn everything that diverges from what busybox can handle.
I would guess it tends towards more likely because it can't not think of something mentioned.
But I agree, I would8 much rather have some data than reckons.
It's with noting that people do this too. They tend to vastly overetimate a low probability event that they know is possible. Often by more than one order of magnitude.
It is something worth keeping in mind when you are people throwing around personal p doom scores.
Interestingly when humans have to make a decision based upon the probability they feel, they tend to act far closer to the actual probability than what they would say the probability is.
I tried a couple of games on my phone that had the phone/tablet tag. They ran and were aware of touch, but everything I tried was not really a mobile targeted experience.
I'm not sure what the correct approach is to handling that. Perhaps a recommended platform so you can find something targeting a type of experience rather than mere compatibility.
Still, every one was better than YouTube games. Not a high bar, but a bar nonetheless.
It’s a tad hit and miss with some of them, as browser does seem to be the default build, but I’ve found a good few on mobile I’ve really enjoyed. I’ll look into what else can be done here - really appreciate you having a look!
What conditions do you need for runaway greenhouse effect at 1 AU. earth has had over 20% CO2 in the past, but the sun was cooler then.
Moving the planet and pulverising with an impact large enough to kill everything are firmly in the bounds of not currently feasible.
I really doubt humans could do it, it would have to be done in one fell swoop, because any attempt to push the earth beyond a tipping point for bacteria to be killed would require pushing for longer than we, the pushers, could survive.
We would have to be better at designing than evolution to make Grey Goo, otherwise evolution would probably have already done it, and it has, to date, designed some pretty out there things.
> Moving the planet and pulverising with an impact large enough to kill everything are firmly in the bounds of not currently feasible.
I mean, it sure seems unlikely, but I'm not as qualified as Dr. Greg Laughlin and his team at NASA, so without at least some kind of evidence indicating that we couldn't do it, I'm okay with trusting them on it being "not at all far-fetched".
'The technology is not at all far-fetched,' said Dr Greg Laughlin, of the Nasa Ames Research Center in California. 'It involves the same techniques that people now suggest could be used to deflect asteroids or comets heading towards Earth. We don't need raw power to move Earth, we just require delicacy of planning and manoeuvring.' (https://www.theguardian.com/environment/2001/jun/10/globalwa...)
Obviously, their plan wasn't to destroy all life on Earth, but to just move the Earth a helpful distance away and then stop, but even in that case they were concerned about sterilizing the planet.
The plan has one or two worrying aspects, however. For a start, space engineers would have to be very careful about how they directed their asteroid or comet towards Earth. The slightest miscalculation in orbit could fire it straight at Earth - with devastating consequences. It is a point acknowledged by the group. 'The collision of a 100-kilometre diameter object with the Earth at cosmic velocity would sterilise the biosphere most effectively, at least to the level of bacteria,' they state in a paper in Astrophysics and Space Science. 'The danger cannot be overemphasised.'
> We would have to be better at designing than evolution to make Grey Goo
Evolution is notoriously bad at designing. It's perfectly fine with a poor or half-assed job as long as the evolving thing typically manages to survive just long enough to make a baby or two. Survival rates can even be outright dismal and design choices absurd if the evolving thing pops out enough babies quickly.
There's a massive difference between intentionally designing something to self-replicate like crazy until all life on earth is either consumed or crushed and just settling for a replication rate that is "good enough, mostly".
reply