Count the RISC processors and RISC ones in your house that isn’t the central one of a PC. You dishwasher, washing machine, tumble drier, TV, routers, WiFi access points, everything else, will be RISC. Normally ARM or MIPS. Apple has gone all ARM. Microsoft are trying to be relevant on ARM. ARM servers are now in low power data centers. RISC-V has a bright future due IP anticompetitive nonsense of x86 and ARM. Oh and x86 has a RISC heart and instruction conversion chips. Which “won” again? ;-)

Also NT is normally said to be a “hybrid” : https://en.wikipedia.org/wiki/Hybrid_kernel

It’s not just the compute, it’s all that data.

As always, have to think where you put your money.

Be so much easier if they weren’t all just different types of bastards!

Oh I know you can run it locally, but I don’t think you can’t create it locally because even if you had the compute, you don’t have the training material.

I don’t know how long AI companies are expecting to run at a loss. It is normal for a while for new bigtech. Though this is new scales. Hopefully this bubble with deflate rather than pop, just because the amount of money will have real world consequences.

Well one way is I don’t depend on it already. But it’s also not like food or water, or grid, society infrastructure in general. It’s just another way of doing compute, but dependent on big tech’s big iron. Being made dependent on big tech is the enshitification. It’s just another method, they have already done all the anticompetition they can. Consumer choice isn’t a solution to regulatory failure, but it’s not nothing.

On top of poltical/power problem, it will have similar effect on software developer brains as satnavs do the navigation parts of our brains. Like satnavs, there will be way to get the good / bad balance better, but that’s not in big tech’s interest. It’s all so damn toxic and drowning open source project in slop PR requests.

Broadly, I see “AI” as part of enshitification. I think it’s brain rotting. It’s commerial setup to get your dependent on it.

That is basically DDoSing open source project, which will not merge code without it being properly reviewed. Almost all open source projects are basically artisan code and the maintainers are the custodians of it.

Is this a technology issue or a human one?

If you don’t understand the code your AI has written, don’t make a PR of it.

If your AI is making PRs without you, that’s even worse.

Basically, is technology the job we need here to manage the bad behavior of humans? Do we need to reach for the existing social tool to limit human behavior, law? Like we did with CopyLeft and the Tragedy Of The Commons.

You sure you can’t do what you need from bash/ssh?

If you only need ssh, anything can be terminal as everything has a ssh client.

It will be faster. It’s also cooler because of the Plan9 history. 😀

VirtioFS. You can share from the host to any number of VMs with that. LibVirtd is good. Even has a nice GUI in virt-manager.