Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Accelerating GPT-5.6 Sol Ultrafast

cerebras.ai

Post reply on HN
Print view View original

271–280 of 295 posts

Re: Accelerating GPT-5.6 Sol Ultrafast

#271

Post by btown »

combustion wrote: post #59
btown wrote: post #49

Earlier quoted context omitted.

There are many industries and situations that will pay absurdly high multiples on API rates for low latency access. Anything remotely related to finance, deal flow, or trading, including the development and checking of Excel financial models. Live analytics that can be delivered mid-meeting to C-suite executives, or ultra-luxe dealmakers who need answers while on a live call. Intelligence and defense, where milliseco…

Please write your own posts

For what it’s worth, I typed every word of my comment above by hand. You’re welcome to see every post that uses sentence fragments, parallel structure, and not-X as a sign of AI, rather than a style learned by a human from decades of personal essay writing and forum discussions. I think that’s a limiting way to see the world.

Re: Accelerating GPT-5.6 Sol Ultrafast

#272

Post by _flux »

shussjjs wrote: post #241
TacticalCoder wrote: post #188

Earlier quoted context omitted.

But speech evolves. And we all pronounce "ten ex" , not "ten times" . Actual speech usage very clearly pronounce the letter 'x'. So it's 10x. And no need for Unicode codepoints.

A number plus an “x” is used beyond Trumpistan. I have never in my life heard anyone say “ten ex”.

Have you heard the expression "10x developer"?

Re: Accelerating GPT-5.6 Sol Ultrafast

#273

Post by kissickas »

rokob wrote: post #193
TranAndrewA wrote: post #189

Earlier quoted context omitted.

Luna came out about a month ago, you're saying that the cost saving from switching to Luna has saved your company $20 000 000+ in 1 months spending on API usage?

It makes sense at a company that sells AI as a service. Perhaps to make presentations...

The ones with terrible slides on their MTA ads?

Re: Accelerating GPT-5.6 Sol Ultrafast

#274

Post by andai »

eru wrote: post #259
andai wrote: post #195

Earlier quoted context omitted.

When I was doing some important work, I had 2 worktrees, each running a frontier model from a different company, and I passed their responses between them in markdown files and had them critique them. I thought they'd prefer their own solutions, but they frequently preferred the other model's solutions. I went back and forth like this until we converged on a solution "everyone" was satisfied with. --- Context: I'm a…

> I thought they'd prefer their own solutions, but they frequently preferred the other model's solutions. I suspect that's downstream from their sycophancy.

Ha, maybe. Sample size was low but usually both models ended up preferring the same solution.

Re: Accelerating GPT-5.6 Sol Ultrafast

#275

Post by andai »

epolanski wrote: post #127
andai wrote: post #120

Earlier quoted context omitted.

I'm finding Luna suprisingly adequate for my work. I slept on it due to the benchmarks, but it's very fast and even on low reasoning I'm finding it more than adequate for "menial" work. (The speed is crucial for "interactive" work -- if a model is fast enough it goes from "async" to "real time", subjectively, which is a huge difference.) In fact, I'd say it's overqualified for the kind of work I'm doing, because it s…

I feel odd to use these models, because it feels like a faster model doesn't feel that much faster if it spends reading files, making edits and running checks. It feels too situational.

Which one of those takes time?

Re: Accelerating GPT-5.6 Sol Ultrafast

#278

Post by christoff12 »

Daneel_ wrote: post #209
TacticalCoder wrote: post #188

Earlier quoted context omitted.

But speech evolves. And we all pronounce "ten ex" , not "ten times" . Actual speech usage very clearly pronounce the letter 'x'. So it's 10x. And no need for Unicode codepoints.

I fully agree that speech evolves, but maybe this is just in the US? I've never really heard anyone say it here in Australia, it's usually "times", although admittedly almost no one uses the phrase/format here.

Ah, yes. My gripe is certainly US American flavored.

Re: Accelerating GPT-5.6 Sol Ultrafast

#279

Post by christoff12 »

krzyk wrote: post #228
christoff12 wrote: post #116

Earlier quoted context omitted.

An irrational gripe of mine is how GPT uses 7× instead of 7x. I recognize that the former is the multiplication symbol, but I don't think it should be used that way.

Interesting I always thought that "x" (whichever) is used informally for multiplication and proper sign is dot: 3 · 4 = 12 It looks like there is a difference between English speaking languages and the rest in that regard.

Funnily enough, I didn't even have the speaking aspect in mind.

I don't like how the "times" symbol floats off the line -- it's a visual thing for me (again, irrational).

Re: Accelerating GPT-5.6 Sol Ultrafast

#280

Post by zuzululu »

aenis wrote: post #211
zuzululu wrote: post #90

Earlier quoted context omitted.

why intel and amd ? these are cerebras wafers? i know people are joking about the sol ultrafast prices (its unlikely to be accessible for average joes) but this shows scaling wafer cores works for inference boost which makes me very excited, sol ultrafast will be as slow as it will get if that makes sense. at these token speeds , we will see a much deeper economic impact.

On large codebases, literally anything I throw at Fable or Opus takes at least 20 minutes, 10 of those minutes is spent on running test suites. With this way of working, I put way more emphasis on test coverage, integration tests, behavioral tests, in-browser tests -- and I run them on every change, before any commit. Faster CPU solves this, while faster inference solves the other 10 minutes. I can't imagine how cool…

gotcha, we got faster inferences but now CPU has to deal with the tasks.
Post reply on HN