But why though? Cannot possibly be useful at such slow speeds, and costs a ton to perform that badly

roadside_picnic 5 hours ago | parent | next [-]

I've never understood why "Hacker" News so frequently gets "But why though?" comments at the top.

The entire history of innovation is filled with people doing something just to see they can get it to work, even if badly, and then people continue to iterate on that until it works better, then works well, and then is so obvious people would never even question it. But it all starts with someone doing it to scratch an itch.

Neural networks, the foundation of our current AI revolution, used to fit well into the "neat, but practically useless" category.

Sure there are countless "but why though?" experiments that don't pan out, but that's just the cost of exploration. There can be no step-function innovation in a world where people only do things that make immediate practical sense.

▲

sixothree 4 hours ago | parent [-]

Gen X here. Having grown up in the 80's I remember multiple occasions where someone would ask "what are you going to do with a computer?". As in, what could a computer possibly be useful for. Just imagine someone asking this question today. It would probably be more shaped like the comment you are responding to.

What are you going to do with a computer? I've always hated this attitude. We do these things because they are interesting to us, for the fun of exploration, because we enjoy learning, because we want to iterate and improve, to make the world better, or any plethora of reasons that involve intellectual curiosity of some sort.

	▲	NooneAtAll3 3 hours ago \| parent [-]
		> "what are you going to do with a computer?" > Just imagine someone asking this question today. to be fair, considering how young folks live whole life in a smartphone nowadays...

▲

nicce 4 hours ago | parent | prev | next [-]

I guess the point of this whole forum is "Why not?"

▲

ganelonhb 5 hours ago | parent | prev | next [-]

I think the point is that it’s running at all…

	▲	Argonautlabs 5 hours ago \| parent \| next [-]
		It actully does the job. Example: every morning it takes 30-40 minutes to generate reports automatically and these reports are being sent as a pdf to read to Telegram.
	▲	cyanydeez 5 hours ago \| parent \| prev [-]
		Qwen3.8-Flash-Next ships with a 51B lookup table that can be read directly from ssd or memory, which greatly improves it's speed and intelligence. It can load at 4bit quant in ~60GB. These demos are maybe useless, but if open models keep progressing, there's going to be some break through that continues whittling down just how much needs to be kept in VRAM, and progressive degredation to regular system ram and to ssds. Afterall, they're not writing anything to these, so saturing all bandwidth could bring models to the masses. all without any help from Zark Muckerberg.

▲

fnetisma 4 hours ago | parent | prev | next [-]

The Github README literally has a "But Why?" section

▲

glimshe 5 hours ago | parent | prev | next [-]

It's not useful for actual work, but the fact it can be run at all shows that we're evolving towards enabling powerful LLMs to run locally.

▲

pianopatrick 4 hours ago | parent | prev | next [-]

I've had the thought that an underexplored use case for llms is treating them as classification machines. Put in a lot of input then ask for a single token classifying the input. Like "does this code have any bugs? reply "yes" or "no""

Doing something like that at 1 token per second may be useful.

	▲	Argonautlabs 4 hours ago \| parent [-]
		That's the one workload this setup is worst at today, unfortunately: output tokens are cheap at 1/s but input isn't — a 512-token prompt takes ~6 minutes before the first token, because prefill currently reads each layer's experts once per 64-row pass (~9 TB of reads for a 1.4 TB model). Fix is scheduling and it's the next thing being built; once prefill reads each expert once per layer, the one-token-out classifier pattern becomes the sweet spot rather than the worst case.

▲

copperx 4 hours ago | parent | prev | next [-]

Because we can. And K3 is frontier-like. Running on a MacBook Pro.

▲

LatencyKills 5 hours ago | parent | prev | next [-]

I hate seeing comments like this on HN. We used to upvote “look at this crazy thing I did” work. Not everything has to make sense or be ground breaking.

It is cool that they got it to work at all.

▲

Argonautlabs 5 hours ago | parent | prev [-]

Not useful for chat, agreed — and I wouldn't pretend otherwise. It's useful for the other kind of work: scheduled, unattended jobs where nobody is waiting on the cursor. My use is day/week/month end review — go through the numbers, flag what doesn't reconcile, draft the report — and there the two things that matter are that the model is good enough to trust with the judgement (K3 is, and it's the full 2.8T model, not a cut-down one) and that the data never leaves the machine.

	▲	voiceeh 4 hours ago \| parent [-]
		>and I wouldn't pretend otherwise. Such of a Claudism. Not criticizing, just noticing.