foltik

The entire point of a temporary visa is for the country to benefit from your labor. How does canceling it on a “whim” benefit anybody?

Do you have anything constructive to say about the merits of the leave to renew policy itself? Or the zero notice halt of visa processing?

Or just vague gesturing about how immigrants aren’t entitled to anything? (but you presumably are!)

Look around the thread and notice how little the comments defending these policies have to say about the policies themselves. Instead, what they all have in common is a vague underlying fear of being displaced, or sense that something owed to them is being taken.

> isn't even trying to have a conversation in good faith.

What about the sweeping halt of all legal immigrant visa processing?

Absolutely not. They put in the literal bare minimum possible effort short of locking down the platform entirely.

You get a jmp to some arm64 instructions of your choosing, with a bunch of CPU features locked out.

It’s barely a “feature” that they let you execute arbitrary code on your own hardware.

They don’t provide any source code or documentation (which they easily could) so if want to do literally anything with your “open” device you must first reverse engineer the entire MacOS driver stack like the Asahi project did. Great fun, but it’s a criminal waste of incredibly talented engineer hours.

On top of that, the reason Asahi doesn’t work on M4 and later is that Apple has intentionally modified the ARM core to prevent stock MacOS from running once the hardware is “unlocked,” which makes it way more difficult to reverse engineer.

Bastards.

Not really. Take Chrome for example. It controls what javascript APIs websites have access to. Still needs separate sandboxing.

Computers are useful because we can instruct them what we want to do precisely.

It’s true we usually don’t care about all the details, which is why abstractions exist. An abstraction hides details by fixing them, and lets you specify the rest precisely.

An LLM isn’t an abstraction in this sense any more than asking a coworker to do something is. The details are not fixed, but decided for you. If you can’t understand or modify what was decided yourself, the only interface left is going back and forth in natural language.

So no, the abstractions won’t become unnecessary. The details don’t just go away. Plenty of people really don’t care about them, and for them the LLM is fine, but only because it’s gluing together the millions of LoC of existing libraries and frameworks where the details have already been fixed, overwhelmingly by humans.

There will always be a need for human professionals who aftually understand all that obscure stuff, and per TFA, it’s looking like it won’t be the ones who went all in on AI.

False dichotomy.

If all your colleague does is generate a “response” in a specific writing style based on some context, there’s no reason to talk to them at all. The good ones have some novel human insight that can’t be approximated by a slop generator.

And if you really want to record all your work and project context somewhere, just let people ... look at that directly? Or summarize and query it with their own LLM if they want to?

No, it’s not relevant to simple GPU offload, stop spam linking your slop blog.

It’s described in this patent application [0]. There’s a bit of hand waving so the HC1 might be slightly different, but the gist is the same.

https://patents.justia.com/patent/20250123802

I avoid closed source software because it’s often a pain to use on Linux.

At least in the case of Taalas the weights are physically encoded directly on the chip.

It’s composed of 4-bit multiplier cells that compute all 16 possible results in parallel. The top metal wiring layer physically selects the one that corresponds to a multiplication with that cell’s constant weight, and routes it to the next layer.

Where do I sign up to get $100M to dump into long AI positions?

Just let them have their AI pacifier.

I read through the explanations and they’re all typical hand wavy LLM prose, full of jargon, and random tangential details. If you’re going to publicly present this as a learning tool, it would be great if you spent some actual human brain cycles writing and polishing it by hand, rather than just chucking the first thing that claude spits out over the fence. I can pretty much guess the prompt you used and probably get the same thing.

No, the reports specifically mention that the AI target selection pipeline drastically increased the workload and expectations of the humans in the loop, leading to spending far less time on deciding whether to attack, iirc a few seconds per targeting decision.

Of course some overworked analyst is going to start neglecting the details and erring on the side of bomb it if the AI summary is dangerous sounding.

It’s gross negligence to be offloading this type of analysis to claude. Do you decide what’s factual based on the google AI summary? They’re deciding to end thousands of lives with about the same amount of rigor, including those schoolchildren. Have some humanity.

Your site has a bunch of marketing copy, trademark symbols, and a link to pay you $2k/mo, but zero technical detail and is broken on mobile. It gives vibe coded.

The benchmark of 2m black-scholes evals/sec is meaningless without additional context. Also seems a couple orders of magnitude slower than what I’d expect even for a single core. What exact transformations are being done, and what’s the throughput in GB/sec? Is it multi threaded? Benchmark against the equivalent query in kdb+ and ClickHouse?

And proving my point:

https://github.com/ChristofferGreen/PrimeStruct/blob/d4f1a8e...

Sounds like they did the ol “grok please make this secure” and it slopped out this plausible-if-you-squint nonsense.

Rendering untrusted model output, ooh scary! Of course we want full audit surface!

Such a spec would never survive contact with reality. Maybe a human could stumble their way through iterating on it with the help of an LLM, but with current models you’re going to end up with nothing but a steaming pile of garbage. Not Zig.

Not really, in such large companies there's enormous selection pressure favoring career politicians. Maybe some of the survivors did some engineering at one point, but expertise fades fast when you stop getting your hands dirty. Most are empty suits.

Yup look at the rest of their comments

I think it’s the opposite. The _distrust itself_ was pushed by those looking to stir up outrage, generate engagement, and turn it into votes.

Case in point: look at all the people who’ve now built their entire political identities atop this unfalsifiable distrust. They’d even distrust “stand further apart” if the wrong person said it.

> I do not know how this trust can be rebuilt but definitely not by publishing more reviews.

This is the crux. Outrage spreads way faster than the boring truth.

Please no. The author would be advised to write their own original thoughts.

What positions did you hear and conclude were baseless?

I don’t disagree. It’s dehumanizing, and they have a legitimate complaint. In almost any other context I’d be on the side of the workers here. I just have a hard time seeing Meta employees as innocent or helpless bystanders.

It’s a bit hard to feel sympathetic here. Those signing this petition actively enable and profit from one of the most pervasive surveillance networks ever built.

Funny how much easier it is to tolerate something when it only affects other people.

Classic. So tell me how I can just not deal with the credit bureaus? Or tax filing companies? Or any site that sells my data to adtech, without totally secluding myself from the modern web? Where’s the supposed competition?

What you’re saying is functionally equivalent to “just deal with it,” since ultimately people will choose to have their privacy violated over the lifelong Sisyphean task of trying to avoid all of that. That doesn’t mean people don’t care about privacy, it’s just the current equilibrium in our broken system.

> I think we have been stuck in this way of life so long we can't imagine an alternative.

I agree.