But another expected scenario is an attacker with a nondescript car and a wifi router inside who can sweep the neighborhood searching thru walls for Person X.

Hmmf, nasty, but labor intensive. Is it working on backscatter ? because your devices shouldn’t be responding much (beyond ping / authentication query level).

Also, at that point they can just use whatever fits in a van, radar, IR scanners, who knows what, fucking X-rays maybe, don’t know that they’d bother with this.

Avoiding it being deployed at scale to everybody’s router might be more important.

If it gets you started with local models, by all means go ahead, their onboarding is the easiest and it works. Also a lot of 3rd party stuff uses it as a first class citizen allowing you to try out other things (e.g. Open WebUI) easily as you explore what’s possible. Currently try the Qwen 3.6 and Gemma4 models as best bang for buck, somewhere there’s a does it fit in my machine website that can help (search for it).

That said, basically all roads in local LLM lead to llama.cpp, which gets the innovations first and then others copy their homework. Ollama (looks like they’re angling to go commercial) for a long time used it internally without attribution, now they use a bodged up engine of their own that is less performant and almost certainly a copy (possibly vibe coded) of llama.cpp. They heavily encourage using their own models / quantizations and don’t let you play with a lot of parameters without a lot of friction (possibly because they’re not implemented yet, but who knows, low transparency). You get the picture, wannabe techbros. That’s off the top of my head, search for more authoritative sources.

After you’ve gotten the hang of things, have a look at llama-swap which just wraps llama.cpp, lemonade if you’re on AMD, vLLM for nvidia, LM Studio for mac.

It’s a (corrupted) router level attack, so the sensible counter is OpenWRT or rolling your own router. I doubt many cheap routers have the grunt to run this anyway.

K, I’ll circle back in a week or so…

Hope so, bet it doesn’t without some tweaking though, OpenAI-compatible seldom is, and ollama is bad for that. Still, worth checking out, I’ll have a go at it sometime soonish and perhaps you’ll see a PR (or some doco in the best case scenario).

Ollama is enshittifying at a rate of knots, have you got a way to use llama-server (or preferably llama-swap) instead ?

Not to mention road-runners (humans) and ACME (OpenAi, Anthropic etc.) extending the metaphor in a different direction… Wile.E. (coyote, suupergenius) might be another name option.

Ahh, ninja’d, I’ll leave it as another vote.

a psychopath, a public threat to society, a terrorist if you will.

I’ve heard it argued rather well that it’s more dread than terror that these pricks create. It’s a useful distinction, but ‘dreadist’ rolls off the tongue like a brick.

keeping the cat in the bag

Just the neoliberal instinct to promote monopoly.

what does Uncle Sam do?

If you have adequate opsec, nothing ;}. At the moment, them pursuing it might provoke other governments to dump those laws, after all the deal was for tariff free trade, turn around is fair play. But manufacturers won’t want to take the legal risk until it shakes out.

I’ve never seen a roadmap

Neither have I, sounds like a good project in itself if it doesn’t exist. ‘Drivers for xyz, reverse engineering something’ is part of the problem, phones usually (nearly always best I understand) have proprietary blobs of firmware to a greater or lesser degree and it’s a moving target different between manufacturers and most often models. Qualcomm modems are particularly egregious for patent reasons. US trade deal enforced global DMCA laws make reverse engineering legally tricky. Hence the desire for linux specific hardware platforms.

I get (and share) the purist hate on saOS’s non OSS UI, but to get linux phones up and running you need app support₁ and market adoption (people buying phones) to make it a viable switch from the walled gardens for more people to use it, to get more hardware made and so on. Chicken and egg deal, bootstrapping. As such anything that gets people in front of linux phones should be embraced at this point, as long as it can run linux native code₂ . When the snowball is rolling, then push for full OSS.

Don’t let perfect be the enemy of good (enough for now).

1: There’s plenty of linux apps but few are designed for small touchscreens. Android emulation often takes us back to non open source anyway, even as it helps adoption.

2: and preferably can be re-flashed with something better later, which is becoming rare as bootloaders get locked down.

Afterwards, “economy in a recession” is synonymous to “free buffet” to those at the reins.

Not at all wrong, but there’s only so much blood parasites can suck before the host dies (and with luck kills the parasites, and / or sends a strong signal to everybody else to get their infestations eradicated, or at the very least under control), and that host is already hurting bad.

Perhaps I’m being optimistic, but a collapse of the likely magnitude could be that straw, or maybe it’ll just be the back of US influence that breaks.

The lower prices could be aimed at undercutting the competition.

Mobster voice: Sure would be a pity if the monetization potential of those 2 huge IPOs (3 if you count SpaceX with xAI deadweight rolled in) went boom when that’s all that’s holding your economy out of recession (depression depending on how they cook the books).

Fuck Zuck, the cuck that sucks.

Yup, easy peasy. And if you really want AI deep research, how about plugging it into your own local LLM with Vane

Interesting to speculate how many of these are “Bullshit Jobs”, which arguably are the only ones AI is capable of replacing. While this may suck in the short term (especially for USians and others without a decent social security net), in the long run it may lead to more fulfilling work.

And that (obviously) is the low hanging fruit. We end up with a more secure kernel, and these filter in at a manageable rate and the bar raises. Pretty damn good scenario IMO.

Closed source is going to have a much worse time.

He profits just fine. The companies not so much.

Except NVIDIA, they’re making shovels and shitloads and he probably gets something under the table from them too.

Sounds like all you need is an Ext4 USB drive with a LUKS key on it. Then add kernel parameters like

rd.luks.key=UUID=/.keys/TheKey:LABEL=KEYS rd.luks.options=discard,keyfile-timeout=10s

in GRUB and it’ll autoboot.

Pull the key and power down and you’re back to normal. I use it in a low threat model environment so I can hit reboot and go get a coffee and come back to a DE.

ETA: sorry, got the timeout format wrong, I don’t use it.

Sounds good. Bonus points for getting it in the media.