withinboredom

I don't think that's how it works. From experience from working on an experimental online learning system... it can't remember verbatim unless it is _really_ in there many many times. It can reconstruct it pretty close though.

source: online learning of codebases in the hundreds of thousands to millions of lines of code

Heh. But an https cert can be used for quite a bit more than just responding on port 443. Like smtp, pop, databases, etc.

As someone who grew up in the US and then moved to the EU; I came here to say exactly this. You leave your private house, get in your private car, then go somewhere. You could live 10 years beside someone and never know their name.

Here in the EU, I know most of the people on my street because I walk by them every day on my way to the store. In the US, even though I lived less than 1 mile/500ish meters from the store, I couldn't walk there if I wanted to.

Wow. Now that is a weird and interesting take. Paying for privacy. Wow. I guess next we will be paying for respect too.

Yeah -- if you want to do something better; set it on the Beale Ciphers.

So, just add a 0 z-coordinate. And fwiw, points are usually represented on a computer with a 4D position, not a 3D one. So; if they specify "3D" then point clouds likely aren't covered.

Couldn’t you argue a bitmap is a “point cloud” in 2D space?

The GPU isn’t connected to the disk though. Usually. So you’d still have to load from disk, to ram, then from ram to the GPU.

I don't wear a watch for health bs. I wear a watch to tell time; the fact that it can also call my family is a bonus. Or show the current weather.

I failed at 2 times. My folding couch couldn't supply the required pressure beyond that point.

Reminds me of a new PM believing that "arabic numerals" mean arabic script instead of real every day numbers because AI told them so. Despite the entire team trying to explain it to them.

Some people would just rather believe a computer than the evidence right in front of them.

If by "understand" you mean to put the hidden state of the transformer into the desired topological basins. Yes, it does "understand" them better.

10 gb per second is pretty slow for a disk. You should be seeing much higher than that.

I didn't know the US had royalty... You should consider moving to the EU if you want to do work for lords and ladies.

The problem is dram bandwidth to the cpu. Each token costs roughly 20gb of traffic and ddr5 is roughly 50-80gb/s, plus you still have to run the compute sequentially. That’s your limit.

Why quantize to int8 when k3 is int4? I could be wrong, but that’s what I remember seeing.

And to clarify -- it only applies to models, not arbitrary data. So its useful to exactly zero other fields.

I honestly don't know... I didn't train the models, so I can't tell why the math works out that way. It just does. I suspect it has to do with the fact that all the small models I've tested have been quantized. I don't know of any small model trained from scratch. If you know of any, I'd be happy to encode it and see what it looks like.

We're not an AI company ... nor do we have any reason to use it. Just a fun idea that was fruitful.

704gb -> 564gb; 358 gb -> 270 gb; 28.79 gb -> 7.65 gb; 439 gb -> 93 gb

It depends on the total entropy of the model. Smaller models have less entropy.

Thanks for your opinion

We have a lossless compression codec (working on open sourcing it over the next couple of weeks) that reduces it down to its minimum entropy -- it cannot be compressed further. On all tested large models, it's a ratio of 1.34-1.23 -- and smaller models up to 3.76x. It also increases the effective bandwidth by the same rate.

I'm pretty sure they can't compel you to enter a password.

They are indeed quite challenging. We literally wrote a paper about it (https://arxiv.org/abs/2605.09114) ... you almost describe some of our original architecture too! You might find it interesting -- or not. https://getswytch.com

I’d also recommend looking at Swytch (docs.getswytch.com, particularly the economics page).

Disclosure: I’m a founder.

I recommend checking out https://getswytch.com ;)

The best kind of correct.

Reminds me of a meeting I was party to with the Safari team. We worked with them on some standards stuff at an old job. They claimed to have creepy-level tracking of users back then. We were discussing how to identify users for an A/B test across millions of sites and comparing what fingerprints we could both derive to most likely end up on the same user.

If you use a closed source browser. That’s the kinda shit they do.