

As if the ONLY thing your memory could be used for is running AI models.
Hey buddy, we need this shit to use our BROWSERS or to play GAMES. I have a GPU in my computer that can run most new AI models when quantized at a speed that would be perfectly reasonable for any home user that doesn’t want it to literally replace every ounce of their thinking, and I bought that shit before ChatGPT was even a thing, because I wanted to play fucking video games.
I have a NAS with 16 gigs of RAM and a consumer-grade CPU that’s a few generations old, and it can still run models with zero GPU or AI accelerator if you give it a little time.
Is it going to be perfectly tuned, and run at the highest possible speed if you design a datacenter just for AI models? Of course it is. But do most people on this planet need that or give a fuck about it? Absolutely not.



This isn’t the case, though I can see how the article could lead you to believe that.
It’s directly based on password rather than key input. The entire vulnerability is that typing a password longer than 256 characters automatically defaults to
crypt()outputting the*character instead of a normal password hash, which is coincidentally the same default character used as the “hash” (not actually a value you could get from a normal hash, intended to be impossible to get from any normal password for that reason) for the built-indaemonaccount.When the Ars Technica article says “Second, the target system account must be configured to be passwordless”, what they mean is the default
daemonaccount, which has a hash set to*by default, and thus wouldn’t normally be accessible via any hashed password… unless you happen to find out that the system chooses to not make a hash, and just send*if you type more than 256 characters.Look at https://sshhole.com/ if you want the details.