That's apples to oranges; your link says they made it exaggerate features on purpose.
"The researchers feed a picture into the artificial neural network, asking it to recognise a feature of it, and modify the picture to emphasise the feature it recognises. That modified picture is then fed back into the network, which is again tasked to recognise features and emphasise them, and so on. Eventually, the feedback loop modifies the picture beyond all recognition."
Does this still work if you give it a pre-existing many-legged animal image, instead of first prompting it to add an extra leg and then prompting it to put the sneakers on all the legs?
I'm wondering if it may only expect the additional leg because you literally just told it to add said additional leg. It would just need to remember your previous instruction and its previous action, rather than to correctly identify the number of legs directly from the image.
I'll also note that photos of dogs with shoes on is definitely something it has been trained on, albeit presumably more often dog booties than human sneakers.
Can you make it place the sneakers incorrectly-on-purpose? "Place the sneakers on all the dog's knees?"
It's not "1,000 wasps or 1 dog", it's "1,000 dogs at once, or "1 dog at once, 1,000 different times". Rare but huge and coordinated siege, or a steady and predictable background radiation of small issues.
The latter is easier to handle, easier to fix, and much more suvivable if you do fuck it up a bit. It gives you some leeway to learn from mistakes.
If you make a mistake during the 1000 dog siege, or if you don't have enough guards on standby and ready to go just in case of this rare event, you're just cooked.
I don't quite see how this maps onto the situation. The "1000 dog seige" also was resolved very quickly and transparently, so I would say it's actually better than even one of the "1 dog at once"s.
Perhaps not, but still compared to running your own thing you just sit and wait. No on call rotas to manage and pay for; no root cause analysis meetings after that descend into internal blame.
When only one thing goes down, it's easier to compensate with something else, even for people who are doing critical work but who can't fix IT problems themselves. It means there are ways the non-technical workforce can figure out to keep working, even if the organization doesn't have on-site IT.
Also, if you need to switchover to backup systems for everything at once, then either the backup has to be the same for everything and very easily implementable remotely - which to me seems unlikely for specialty systems, like hospital systems, or for the old tech that so many organizations still rely on (and remember the CrowdStrike BSODs that had to be fixed individually and in person and so took forever to fix?) - or you're gonna need a LOT of well-trained IT people, paid to be on standby constantly, if you want to fix the problems quickly, on account of they can't be everywhere at once.
If the problems are more spread out over time, then you don't need to have quite so many IT people constantly on standby. Saves a lot of $$$, I'd think.
And if problems are smaller and more spread out over time, then an organization can learn how to deal with them regularly, as opposed to potentially beginning to feel and behave as though the problem will never actually happen. And if they DO fuck up their preparedness/response, the consequences are likely less severe.
Alternatively, you can download Firefox Nightly instead of regular.
"about:config" just works in Nightly. No fuss.
You can sideload extensions in Nightly, too, after you activate the developer options. I don't think they've added that to regular, as yet? At least not with as much flexibility.
Anyway, I'm gonna try this mobile desktop mode thing and see how it goes. Thank you to everyone!
Installing extensions from file is available on the release build as well, after enabling dev options.
I think the only difference is nightly allows installing unsigned extensions, which I don't personally have a need for (as getting a personal/non-published extension signed is very easy).
"The researchers feed a picture into the artificial neural network, asking it to recognise a feature of it, and modify the picture to emphasise the feature it recognises. That modified picture is then fed back into the network, which is again tasked to recognise features and emphasise them, and so on. Eventually, the feedback loop modifies the picture beyond all recognition."
reply