Live data from Hacker News

QwQ: Alibaba's O1-like reasoning LLM

qwenlm.github.io

211–220 of 435 posts

Re: QwQ: Alibaba's O1-like reasoning LLM

#211

Earlier quoted context omitted.

Apple silicon is pretty damn viable.

Yeah, but if you buy ones with enough RAM, you're not really saving money compared to NVIDIA, and you're likely behind in perf.

Nvidia won’t sell these quantities of RAM at Apple’s pricing. An A100 80GB is $14k, while an M3 Max MBP with 96GB of RAM can be had for $2.7k.

Re: QwQ: Alibaba's O1-like reasoning LLM

#212

Earlier quoted context omitted.

That is a pretty dark view on almost 1/5th of humanity and a nation with a track record of giving the world important innovations: paper making, silk, porcelain, gunpowder and compass to name the few. Not everything has to be around politics.

> That is a pretty dark view on almost 1/5th of humanity The CCP does not represent 1/5 of humanity. > and a nation with a track record of giving the world important innovations: paper making, silk, porcelain, gunpowder and compass to name the few. Utter nonsense. It wasn't the CCP who invented gunpowder. If you are willing to fool yourself into believing that somehow all developments that ever originated by people w…

You changed china with ccp for both statements and then corrected them.

Re: QwQ: Alibaba's O1-like reasoning LLM

#213

I asked the classic 'How many of the letter “r” are there in strawberry?' and I got an almost never ending stream of second guesses. The correct answer was ultimately provided but I burned probably 100x more clockcycles than needed. See the response here: https://pastecode.io/s/6uyjstrt

I was about to give it some credit for being thorough, even if overly so. But then I noticed these gems:

   thinking about the phonetics, "strawberry" has three /r/ sounds...

   For example, in Spanish, it's "fresa," which has no "r"s, or in French, "fraise," which also has no "R"s...

   But to be absolutely certain, let's count them one by one: s-t-r-a-w-b-e-r-r-y. Okay, the first "r" is after the "a," then after the "b," and finally twice at the end before the "y." Wait, is that two or three "r"s at the end? Let's see: s-t-r-a-w-b-e-r-r-y. So, r-a-w-b-e-r-r-y. Okay, there are two "r"s before the "y." So, that's one after "a," one after "b," and two before "y," making it four "r"s in total. Wait a minute, now I'm confusing myself...

   For example, "copyright" has two "r"s, "arroba" has one "r,"...

   Wait, perhaps I'm confusing it with "arrowroot," which has two "r"s. Alternatively, maybe thinking of a word like "corroborate," which has four "r"s...
and

   Alternatively, thinking about Middle English "strawberie," still three "r"s.
It's not being thorough. It's just trained to sound like it's being thorough. It's producing the same garbage as any other LLM, this one just happens to get the answer right because it's been trained on data that includes discussions of the strawberry problem.

There's certainly a unique mechanism which might make it better at searching a space for answers, and that's pretty neat in its own way.

Re: QwQ: Alibaba's O1-like reasoning LLM

#214
post #132

I asked the classic 'How many of the letter “r” are there in strawberry?' and I got an almost never ending stream of second guesses. The correct answer was ultimately provided but I burned probably 100x more clockcycles than needed. See the response here: https://pastecode.io/s/6uyjstrt

Well, to be perfectly honest, it's hard question for an LLM that reasons in tokens and not letters. Reminds me of that classic test that kids easily pass and grownups utterly fail. The test looks like this: continue a sequence: 0 - 1 5 - 0 6 - 1 7 - 0 8 - 2 9 - ? Grownups try to find a pattern in the numbers, different types of series, progressions, etc. The correct answer is 1 because it's the number of circles in t…

These tests always make me wonder: What qualifies as a valid pattern rule?

For example, why wouldn't "0" be a correct answer here (rule being "every other number on the right should be 0, other numbers do not have a pattern")?

Re: QwQ: Alibaba's O1-like reasoning LLM

#215

Earlier quoted context omitted.

Also a nation that just used their cargo ship to deliberately cut two undersea cables. But I guess that's not about politics either?

The ship was not driven by China, the media reported it incorrectly first.

Do you have a source more recent than https://archive.is/3weox (WSJ article)?

It appears to be a Chinese ship, although it is not clear that the Chinese government sanctioned whatever happened.

Re: QwQ: Alibaba's O1-like reasoning LLM

#216
post #58

Earlier quoted context omitted.

I don’t see why they wouldn’t. If you’re China and willing to pour state resources into LLMs, it’s an incredible ROI if they’re adopted. LLMs are black boxes, can be fine tuned to subtly bias responses, censor, or rewrite history. They’re a propaganda dream. No code to point to of obvious interference.

That is a pretty dark view on almost 1/5th of humanity and a nation with a track record of giving the world important innovations: paper making, silk, porcelain, gunpowder and compass to name the few. Not everything has to be around politics.

You say that as if it isn't warranted.

https://en.wikipedia.org/wiki/Document_Number_Nine

Re: QwQ: Alibaba's O1-like reasoning LLM

#217
post #132

I asked the classic 'How many of the letter “r” are there in strawberry?' and I got an almost never ending stream of second guesses. The correct answer was ultimately provided but I burned probably 100x more clockcycles than needed. See the response here: https://pastecode.io/s/6uyjstrt

Well, to be perfectly honest, it's hard question for an LLM that reasons in tokens and not letters. Reminds me of that classic test that kids easily pass and grownups utterly fail. The test looks like this: continue a sequence: 0 - 1 5 - 0 6 - 1 7 - 0 8 - 2 9 - ? Grownups try to find a pattern in the numbers, different types of series, progressions, etc. The correct answer is 1 because it's the number of circles in t…

a possible lesson to infer from this example of human cognition, would be that LLMs that can't solve the strawberry test could not be automatically less cognitive capable that another intelligent entity (humans by default).

An extension of the idea could be that many other similar tests trying to measure and/or evaluate machine cognition, when the LLMs fails, are not precisely measuring and/or evaluating anything else than an specific edge case in which machine cognitions fails (i.e. for the specific LLM / AI system being evaluated).

Maybe the models are actually more intelligent than they seem, like an adult failing the number of circles inside the graphical image of the numbers, in the mentioned problem.

Re: QwQ: Alibaba's O1-like reasoning LLM

#218
post #191

Earlier quoted context omitted.

I am running it on a 32G memory mac mini with an M2 Pro using Ollama. It runs fine, faster than I expected. The way it explains plans for solving problems, then proceeding step by step is impressive.

How many tokens per second?

I am away from my computer, but I think it was about 10/second - not too bad.

Re: QwQ: Alibaba's O1-like reasoning LLM

#219

Earlier quoted context omitted.

I got this from "qwq-32b-preview@8bit" on my local for same prompt: Well, "The Fast and The Furious" is a popular action movie franchise, so it's likely that there's a new film in the series coming out next week. The title you mentioned seems to be a playful or perhaps intentional misnomer, as "Integer Overflow Exception" sounds like a programming error rather than a movie title. Maybe it's a subtitle or a part of th…

And then still people are saying: these are just heuristic next token predictors incapable of reasoning.

What's weird, is that they are heuristic next token predictors. But that prediction, mixed with a little randomness is producing very seemingly "reasoned" responses.

Re: QwQ: Alibaba's O1-like reasoning LLM

#220
post #132

I asked the classic 'How many of the letter “r” are there in strawberry?' and I got an almost never ending stream of second guesses. The correct answer was ultimately provided but I burned probably 100x more clockcycles than needed. See the response here: https://pastecode.io/s/6uyjstrt

Well, to be perfectly honest, it's hard question for an LLM that reasons in tokens and not letters. Reminds me of that classic test that kids easily pass and grownups utterly fail. The test looks like this: continue a sequence: 0 - 1 5 - 0 6 - 1 7 - 0 8 - 2 9 - ? Grownups try to find a pattern in the numbers, different types of series, progressions, etc. The correct answer is 1 because it's the number of circles in t…

I think it's a "just so story" myth that children are better than adults at that task.
Post reply on HN