Hacker Newsnew | past | comments | ask | show | jobs | submit | oh_no's commentslogin

we've seen anthropic numbers, inference is not being subsidized by these companies

> inference is not being subsidized

Inference doesn't have to be sold below direct compute cost to be subsidized. If inference pricing doesn't cover amortized capex and the cost of capital it's still using investor money to buy market share.


Did you read what they wrote carefully?

Blade Runner is a very interesting exception, while depopulation has become common in speculative fiction these days having it as part of something from the 80s was pretty rare. I don't know when the overpopulation/depopulation switch flipped in fiction, but I think it was pretty recently.

Blade Runner the movie looks anything except depopulated. Well, excluding the vast empty building where Deckard lives. The city is enormous and literally blowing up gigantic amounts of energy and pollution; the streets are packed with people, languages, and clutter of all types (a PKD obsession). In some ways it is fully within the overpopulation zeitgeist of the times.

It's just LA to be honest.

Busy everywhere but also downtown is full of empty buildings and you still need to commute from Glendale even if you're an LA detective running down replicants.

Ads are talking up off world colonies in Texas.

No traffic though, so that's where it's fiction.

Really though the entire fiction relies on the contrast of inventing slaves in giant, monstrous firms while still having plenty of forgotten underclass, huddling in the lower ruins. Deckard is middle class, commuting from his empty suburb to prop up the system.


Isaac Asimov's Daneel Olivaw series of books had the overpopulated Earth alright, but it also had spacer colonies on distant planets that very much kept their populations at a sensible level and were magnificently wealthy in comparison because of it (and robots).

there's a short story, which i think is Asimov's, about a probe reaching earth. and it only detects two life forms in a fully automated planetary extraction mechanism. And those two are forever occupied trying to struggle the remaining half from one another.

> What's really going on?

him sleeping around, hth


i'm actually pretty okay with non-voting shares, it's super voting that are the issue

Those are the same thing.

you sure about that?

How and why would you?

that first video sure is some slickly produced slop that occasionally looks good

the winning benchmark is much more expensive than what it cost for the same on 5.1

i'm begging people to stop looking at token prices


What surprised you about this? This seems pretty in line with optimization work seen from a wide range of models.

Did you try doing the same on Opus or others? How did they do?

I don't love these "look, this frontier model blew me away" comments when there is no point of comparison.


We tried it with Fable 5.1 as well, which was 3-4x slower than 5.2. We also have a blog with benchmark and details if you're curious https://discoveredmaterials.com/research/accelerating-quantu...

I searched for "5.1" in your blog post, and the only hits are in the benchmark numbers.

I agree with GP: without a comparison to Opus 5.5 or some other models, it's not clear how much of an advance this is. If anything, my experience is that performance optimization in existing codebases is something existing models are already great at: it's measurable (you directly profile or try experiments to see what works) and the code architecture is usually relatively fixed (at least relative to deep/greenfield work where there are large architectural questions to be addressed). Newer models might be better at generating ideas for things to try, but if you're getting 36x then it honestly sounds like you have a lot of low-hanging fruit.


Hey for once I feel qualified to reply on a HN thread (I'm one of the developers of DFTK, a similar package). Very nice result. I'm not particularly surprised, as QE is not particularly GPU optimized. I've heard that the QE developers interested in GPU are doing it in Sirius, but I don't know much about it. More generally there's a tension between new features / optimizations and maintainability. I'm not sure how to deal with this medium term. Perhaps having two code bases, one for humans and the other for AI, is not the worst solution.

This sounds very much in line with most reports from people getting early access to models over the last years. Maybe it actually is a lot faster, but it may as well be the load on it not being very high yet. I'll keep my excitement until it has been adopted by the masses.

> What more do people want?

well, releasing it would be nice


Gemini 4 Argon is available in both anti-gravity and the Gemini app for me on my Gmail account and I didn't do anything special (I have a modest drive storage subscription - not the largest nor smallest... Not sure if it is bundled with that or not).

So certainly released to the unwashed masses like me to use for free without any special extra work or API keys.


1. a lot of people do 2. most of their revenue comes from api pricing

Those are both true, but I don't see how they are meant to rebut what I said.

Most people on plan use do NOT use up all their plan usage.

Users on API plans can still use Opus 5.5 which is a great model. If they want top of the line performance, they can pay more.

When another company puts out a model that undercuts Fable 5.2 on price at similar performance, Anthropic will put out Opus 6 and undercut them right back. That's how the wheel turns. This is just part of the cycle.


It rebuts what you said because your statement that "the cost per task matters relatively little" is not true in the slightest.

This might be true for a small portion of the user base, but it is not true as a statement of fact.


... is it?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: