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

VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

arxiv.org

Post reply on HN
Print view View original

51–60 of 226 posts

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#51

Post by dminik »

numlock86 wrote: post #26
secretslol wrote: post #23

Am I right in thinking this is a tiny model which has been trained well to reason, and that's it? Makes me think of a smart person who doesn't know anything about a given topic, but with the right tools will go and research the heck out of it. I really like the sound of this... why have models train on learning anything when you can just train them how to learn and let them get on with it from something as small as a…

This has been my dream ever since. Instead of encoding "all the knowledge" into those parameters, how about just making a model that has the same size, but all (or rather most) it does is reasoning? Just give it the ability to browse the net (e.g. language specifications, documentation and best practices) and just have it do its thing. Why does my coding agent need to know the population of New York, know a cheese ca…

I mean, this really doesn't sound useful even if LLMs worked that way.

First, if you know nothing you don't even know what you're missing or what to search for.

Then, without unlimited context, you have to do research for every task all over again every time.

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#52

Post by trick-or-treat »

nsingh2 wrote: post #39
nsingh2 wrote: post #25

Earlier quoted context omitted.

Lots of confusion about what this model is actually focused on. It is a cheap specialist for closed-world, verifiable reasoning tasks like math, self-contained coding problems, and similar. "Closed-world" means the needed information is already in the context. It is not a tool-using agent that can discover missing context. "Verifiable" means answers are hard to generate but easy to check. So no open ended research, r…

To follow up on this, I had it solve a nasty ODE problem that I saw in the recent Mathematica 15 release post: Solve the following first-order ODE for f(x): ((-1 - 2*x)*f(x)*tan(1 + x - exp(-61 - 2*x)*f(x)/x) + exp(61 + 2*x)*x*(1 - x*tan(1 + x - exp(-61 - 2*x)*f(x)/x)) + x*tan(1 + x - exp(-61 - 2*x)*f(x)/x)*f'(x)) = 0 Find the general solution f(x). And surprisingly it found a valid solution! Extra impressive because…

How do we know the solution isn't in the weights though?

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#53

Post by spacebacon »

zkmon wrote: post #46

Does python coding depend on political facts of the world? It might appear not, but actually, the process of reasoning is not an isolated act. The right and wrong way of doing things is codified in social evolution that absorbed all facets of life. Why should you optimize a piece of code for performance? Why performance is needed? What is a bug? What features and UI themes would be more intuitive for humans? There is…

[dead]

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#54

Post by kame3d »

nsingh2 wrote: post #39
nsingh2 wrote: post #25

Earlier quoted context omitted.

Lots of confusion about what this model is actually focused on. It is a cheap specialist for closed-world, verifiable reasoning tasks like math, self-contained coding problems, and similar. "Closed-world" means the needed information is already in the context. It is not a tool-using agent that can discover missing context. "Verifiable" means answers are hard to generate but easy to check. So no open ended research, r…

To follow up on this, I had it solve a nasty ODE problem that I saw in the recent Mathematica 15 release post: Solve the following first-order ODE for f(x): ((-1 - 2*x)*f(x)*tan(1 + x - exp(-61 - 2*x)*f(x)/x) + exp(61 + 2*x)*x*(1 - x*tan(1 + x - exp(-61 - 2*x)*f(x)/x)) + x*tan(1 + x - exp(-61 - 2*x)*f(x)/x)*f'(x)) = 0 Find the general solution f(x). And surprisingly it found a valid solution! Extra impressive because…

Interesting!

I just tried the quantized Q4_K_M from [1] in my RTX 2070 Super, it ran at 110 tok/s with 1800 tok/s prefill, and found the same solution to your prompt. It generated valid LaTeX for the answer but its reasoning trace uses mostly compact ASCII math notation. Took 3min 22s to answer, spending 22k tokens almost all on thinking.

[1] https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#55

Post by avereveard »

swiftcoder wrote: post #45
deftio wrote: post #16

There is some base level of intelligence any model needs to be useful, even in narrow tasks. Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge... Small models need to have enough…

> To drive a car requires being able to read Emphatically, it does not. Passing your drivers test may require being able to read, but plenty of illiterate people around the world drive just fine. There is a reason we made all the common road signs recognisable purely by shape/colour, after all.

Until they reverse on a highway and kill a family. Being able to drive isn't where parent poster put the bar

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#56

Post by attila-lendvai »

ygjb wrote: post #30
deftio wrote: post #16

There is some base level of intelligence any model needs to be useful, even in narrow tasks. Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge... Small models need to have enough…

> Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge... I would be interested to see a formal study of this. I say this not out of anything other than a observation that I think t…

if you don't sit in the car you lack a lot of information. driving without them is almost a different skill.

(i'm above average in both)

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#57

Post by swiftcoder »

embedding-shape wrote: post #48
satvikpendem wrote: post #32

Earlier quoted context omitted.

While I agree with your assessment, probably could've chosen a better example, as in many countries young kids even as young as 8 will learn how to drive.

In some countries they even let kids as young as 16 drive, no wonder they have so many accidents.

Several US states will give you a permit to drive a farm vehicle on public roads at 14. Illinois recently passed an amendment to allow farm kids to drive a semi-truck at 16. And there is absolutely no minimum age for driving so long as you are on private land - I have seen 8 year olds driving a pickup truck round a farm...

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#58

Post by swiftcoder »

avereveard wrote: post #55
swiftcoder wrote: post #45

Earlier quoted context omitted.

> To drive a car requires being able to read Emphatically, it does not. Passing your drivers test may require being able to read, but plenty of illiterate people around the world drive just fine. There is a reason we made all the common road signs recognisable purely by shape/colour, after all.

Until they reverse on a highway and kill a family. Being able to drive isn't where parent poster put the bar

I don't see what reading has to do with knowing not to reverse on a highway. It's not like they put up big glowing signs that say "wrong way" like in a video game.

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#59

Post by regularfry »

dminik wrote: post #51
numlock86 wrote: post #26

Earlier quoted context omitted.

This has been my dream ever since. Instead of encoding "all the knowledge" into those parameters, how about just making a model that has the same size, but all (or rather most) it does is reasoning? Just give it the ability to browse the net (e.g. language specifications, documentation and best practices) and just have it do its thing. Why does my coding agent need to know the population of New York, know a cheese ca…

I mean, this really doesn't sound useful even if LLMs worked that way. First, if you know nothing you don't even know what you're missing or what to search for. Then, without unlimited context, you have to do research for every task all over again every time.

> First, if you know nothing you don't even know what you're missing or what to search for.

RAG on the initial prompt would be the first thing to try.

> Then, without unlimited context, you have to do research for every task all over again every time.

Thing is, we're really really good at building very fast search engines. Doing research all over again every time shouldn't be a problem.

Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

#60

Post by madduci »

threatripper wrote: post #37
deftio wrote: post #16

There is some base level of intelligence any model needs to be useful, even in narrow tasks. Could you teach a 5 year old to drive a car? A 10 year old? A 12 year old? To drive a car requires being able to read, to have judgement about ice or rainy conditions, to anticipate a child running after a ball. By the time a human in in their mid teens they have acquired the base knowledge... Small models need to have enough…

Ask people who grew up on a farm in a rural area. Sometimes you have to even if you can't and you do.

True story, they can already drive a tractor at 10 and I know people who learned to drive a proper truck at 13 too
Post reply on HN