I'm comparing 0 GPS assist with full assist. Takes a few seconds and another few for a proper lock.
With assist it's kind of instant. But I'm close to Polar Circle, maybe it's less sats over the North Pole?
We keep paying ever higher architectural prices for system isolation: user accounts, memory protection, unix permissions, capabilities... and it's all for nothing, when a determined program can almost always escape its sandbox. Should we just give up and assume that all software on a machine is cooperative and non-malicious, and just do our best to make sure we don't run malware in the first place? "Defense in depth" soon slips into "don't worry too much about this layer, the next layer will catch it.
tl;dr Just run as root bro, focus on the exterior attack surface, and don't download random crap.
I heard a story that before there was the internet, when various defense labs with computers wanted to send data to each other they would load the data onto a drive and then send it over to the other defense lab using a truck and a couple armed Army guys.
That seems like it would still be secure. These days you could even encrypt the drive...
This is also from the era (and probably still true today) where it is easier as a mid-level dude in the Army to get an armed escort to another location than it is to get permission to mail something USPS.
One silver lining I haven't seen discussed much on HN: The latest LLM agents are good at decompiling binaries, which should help detect supply chain attacks.
I suppose the next round will involve supply chain attackers including bioterror-related symbols in the poisoned binary so LLMs will refuse to decompile it.
Anyways, I'm hoping someone will create an open-source project which distributes the work of binary analysis, with binary certification and user reputation systems etc.
This would also be an excellent goodwill project for one of the big AI companies, since this whole situation is kinda their fault.
How can they simultaneously argue that 1) this is a patent infringement, the entire legal basis of the claim, and 2) it is a unlicensed disclosure of proprietary technology? The whole point of patents is to disclose technology.
In that case, most of the information in every single color digital photo is "hallucinated", because each sensor pixel only captures red, green, or blue, in a checkerboard pattern called a Bayer array; we get uniform RGB photos by applying heuristic interpolation algorithms to (shall we say?) "infer" the missing data.
Is "deterministic" really the right line to draw? On the one hand, this is "deterministic", in the sense that (given a fixed model) the same photo will produce the same depth estimation. On the other hand, even film isn't deterministic, with its random grain. But at least random grain looks random. Perhaps the issue at play is really "indexicality", where perceptible signal should be caused by the scene. But even that is fuzzy. What, qualitatively, is the difference between "touching up" and AI enhancement? It's all just algorithms that combine a starting photo with some knowledge of how humans like photos to look. Again, not even film is free of this - when chemically developing, the choice of how strong a developer to use and how long to leave it in has as much effect on the image as the exposure settings chosen by the photographer. There's nothing "deterministic" about a lab technician eyeballing your photos and tweaking the development process.
this is not what I meant. If I take my pro-sumer camera, and take a pictures, photons from reality hit the sensor after passing through a few layers of hopefully high quality glass. So far a lot of messy physics is involved and then there is the bayer array business and math is used to torture those poor photons into pixels. But then. I got a RAW file, maybe 10bit depth, maybe 12, sometimes even 14, more than a jpeg.
Then I go and do things with exposure zones, define highlights, increase the lumina of certain ranges and so on. A lot functions that result in one final receipt. If I take the same receipt with the same raw I reasonable expect the exact same result. The resulting, although manipulated picture, is deterministic in a sense. As soon as an LLM gets involved it is not.
This is the point where I cannot really be in the conversation anymore, I dont understand how the Mariegold Transformer works. Like, I dont know how repeatable it is. I cannot refute or confirm your words. The only thing I can do is nitpick, I am quite sure its not an algorithm as it is a diffusor model as far as I understand it
I feel like you are saying "deterministic", when what you really mean is "predictable". They're all algorithms, just a bunch of multiplies and adds on the image data really. But the algorithms you don't mind are the ones where you feel you have a good intuitive grasp of what they'll do. The ones that seem eerie and break your sense of indexicality are the ones where 1) you're not sure what it will do, and relatedly 2) seem to introduce a substantial amount of new information, perhaps drawn from some database of how images look generally.
To sum up: Marigold V2 is just as deterministic as Bayer demosaicing. But Marigold has about 20 billion magic numbers in it, thoroughly dwarfing the source image. It feels less like transforming the image with Marigold, and more like steering Marigold with the image. And who knows what's in that thing or how it works...
(note: I see the same confusion often in conversations about LLMs. People call them "nondeterministic", as if that were some new category of software. But, with temp 0, they're no less deterministic than any other pile of floating point math - and nobody complains that fluid simulations aren't deterministic. No, what they are is unpredictable.)
This was the core premise of your original comment!
I'm not sure how you define algorithms, but I have a feeling it's not a universal definition. I would argue that diffusion is an algorithm like HDR compensation. Both describe well defined and repeatable processes that can be broken down into low-level components with different potential implementations.
How does your HDR algorithm select a exposure curve for tone-mapping? How does it handle noise rejection? Does it apply any non-local corrections or smoothing? Does the existence of these questions mean that HDR is less of an algorithm? Where do we draw that line?
The selective censorship of faces in the photos but not the depth maps strongly undermines their assertion that they believe they are "detailed enough to become the artwork" and "a new way to approach taking pictures". Ironic, because many of the faces can indeed be resolved in the depth maps. A curious blind spot.
Yes, but that's hardly obvious. I was wondering if it triggered some kind of "update" that permanently altered functionality. Such things are not unknown.
Games are designed to incentivize you to stay in them. Real life has you as a captive audience, and to the extent that it's "designed", it is designed by people also playing the game, against you who have no incentive to encourage you to try harder to beat them.
reply