zstd with better compression level would be nice - these numbers are not really comparable since both time and compression level are too different

Tell that Apple and Android. I have 32 bit native software which can't run on modern devices at all.

I'm sorry to hear that. Could it be ARM related?

Apple dropped 32 bit support in specific OS version with no way to run it anymore sans downgrading the OS - so it's not hardware restriction

It's just to reduce the maintenance burden of backwards compatibility.

> early hours of the morning

which TZ?

> There are no off-peak hours.

Probably US west coast hours, but there's no public stats

2AM CST

Dunno. Crease almost invisible when screen is on and not pitch black ( using Honor V3 while actual generation is V6).

Does that also mean owner must re-run very model ever released by them to detect anything?

1) That's a lot more entropy to gather, means sample size needs to be huge.

2) this also means check must be run against every user's ID in their database, 10^9 more expensive

That makes sense, though it sounds like it would still be feasibly cheap to only track a handful of users or organizations

Do i understand correctly - to check watermark you need full model weights, of all org models. So running the check is basically the same as running every model once? That's really expensive

I don't know the details of their implementation, but in general, if the text is not watermarked, you will probably fail the test after a few tokens. If it is, you will have to run the entire text, or, you can just run it until you have some degree of confidence.

That would be Sv, not SV.

Why bother with macos version at all then? Soon current version becomes unusable as well, and needs windows fallback to run since macos version is useless

If there's a macos port, it'll of course be better optimized. I play CS2 on mac from time to time. It runs really smoothly on my Studio, but if it were a native port I could run it on a macbook air.

*for a brief moment it actually runs.

from the point of the dev - work done on the port will rot very soon, return of investment is really low. Also, the studio may not exist at all by time changes will be necessary - as fast as few days after public release nowadays :(

> It trades something fungible and incredibly cheap (CPU)

it could be RAM-bound, which is very much NOT cheap nowadays :)

It doesn't make the economics any different. In a browser environment, you're maybe looking at the acceptable lease being 100MB for 1 second. Much more than that, and you start hitting limits of what browsers will let you do on low-end phones. Longer than that, and we're back to the user-observable latencies being too long.

100MB for 1 second just is not much of a deterrent.

Yes, but the people with the RAM nowadays are the data centers, not the end users.

Sure, but end users as a group still have a significant amount of RAM.

Even on a low-specced machine you can afford to have the currently-active website tab consume a few hundreds of megabytes of RAM. It was mostly sitting idle anyways, so most people aren't even going to notice. Multiply that by a few thousand concurrent visitors and you're burning hundreds of gigabytes without anyone caring.

Some scraper being forced to install hundreds of gigabytes of extra RAM in their crawling node? They will notice having to go from a $0.50 / h instance to a $15.00 / h one, solely for the extra RAM requirement.