Live data from Hacker News

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

arxiv.org

121–130 of 226 posts

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

#121
How would you best utilize a model like this for coding? I take it it's not meant for vibe coding a full app, and the reasoning probably makes it unsuitable for autocomplete. Would you use it to implement specific functions? I looked at one of the coding benchmarks used, Live Code Bench, and it seems to be problem descriptions with sample input and output, and then a solution with a single function or class.

Seems like a really good model to use in an IDE when you still want control over the code structure then.

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

#122
post #110

Looks like we are seeing small but mighty model breakthroughs, outpacing the pure capital firepower of SOTA providers. I love rooting for the little guy, but is it too soon to call it? To play devils advocate, could it just be the benchmarks are not efficient enough to capture success of real developer workflows?

I've just started using qwen3.6:35b a couple days ago running on my framework desktop and rather impressed. It runs really well and reminds me of probably the first Claude model I used. It's the first local model that's actually working for me in a coding agent I've tried. Very exciting!

Could you please share which coding agent you are using with it?

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

#123
post #110

Earlier quoted context omitted.

I've just started using qwen3.6:35b a couple days ago running on my framework desktop and rather impressed. It runs really well and reminds me of probably the first Claude model I used. It's the first local model that's actually working for me in a coding agent I've tried. Very exciting!

Try 27b, it's significantly smarter than 35b-a3b (although it is slower, it's not so bad with MTP).

At least according to gertlabs, Qwen3.6 27B outperforms every SoTA (closed) model at Kotlin: https://archive.vn/RYBCL / https://gertlabs.com/rankings?mode=agentic_coding&language=k...

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

#126
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, 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...

It is really strange to see comments like this here, where people seem to reduce some basic human action into how it would work in a text-only computer game. Driving itself requires mainly muscular memory how to operate the car, which why people who drive a lot can just go on autopilot and think something completely different when driving long distances. That is of course a form of kno, but you only get it through repetition. Of course driving in traffic requires far more, basic understanding of traffic law etc, but most of driving is muscle memory, understanding the vehicle and anticipating future occurrences. Why we apes are so good at this is because we have some million years of evolution of just using our bodies and seeing what happens. And of course we all seen the gif of an orangutang driving a golf cart (how real it is I’m uncertain), so there’s that.

I think might help to think models not as some future replicants, but models with certain capabilities in certain domains. It probably doesn’t make much sense to ask Opus 4.8 to drive you around as it doesn’t make sense to except a small image model made for edge devices to be able to write a novel. Perhaps we should just think of them as tools with certain applications they are made for.

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

#127
post #122
post #110

Earlier quoted context omitted.

I've just started using qwen3.6:35b a couple days ago running on my framework desktop and rather impressed. It runs really well and reminds me of probably the first Claude model I used. It's the first local model that's actually working for me in a coding agent I've tried. Very exciting!

Could you please share which coding agent you are using with it?

Pi

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

#128
post #44

Earlier quoted context omitted.

I think you could probably train a model to consider boolean logic, modal logic, and mathematics reasonably well, but there is still a pretty big leap between that and thinking about things. Even the most basic questions such as put a ball in a cup and place it on a table upside down then pick up the cup and put it in a box. Requires knowledge of things not mentioned in the question (notably gravity). Strict definiti…

> Even the most basic questions such as put a ball in a cup and place it on a table upside down then pick up the cup and put it in a box. I do not think this is a great example. First, it is not a question. Second, it seems very related to robotics. A model itself cannot put a ball anywhere, it can just call tools and answer in text, image, etc. An LLM seeing "put a x in a y and place it on a z upside down then pick…

The thing is we tried that for decades, using more formal logic to build reasoning engines. And we never got it to be even a fraction as good and generic as learning-based LLMs are today.

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

#129
What are the implications of local SOTA inference, given the insane datacenter "investing" ?

It surely cannot be justified only for training at this scale, and since models nowadays are improved more and more by fine tuning than re-training from scratch.

Will a viable local model crash the US economy ?

More importantly, are the LLM companies aware, and are they deliberately buying out all the RAM and GPUs in order to prolong the inevitable ? Probably not, but I wouldn't be surprised if that is the case.

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

#130
post #77

Earlier quoted context omitted.

I think this is a well known concept, which we can't deliver yet. LLM/transformer give us reasoning engine as a byproduct of its design, but it is quite ineffective. If we can distill reasoning, if reasoning can be achieved without general knowledge, it will be a very effective machine. Some amount of knowledge is required for reasoning. Maybe such model can dynamically knowledge domains to have taxonomy. For example…

>Some amount of knowledge is required for reasoning. This is the root of problem. If you think about STEM universities, they don't really teach you things you need in the real world. They teach you what you need to know in order to go out there and accumulate the necessary information which can then be used to solve problems. Giving a person access to the internet or a super powerful calculator (like Mathematica) won…

Take mathematics as an example. Humanity has found math notation, which allowed to express math rules — distill them to the core. Before math was expressed in prose — a very inefficient way, very similar to current LLMs.

In my school, math teacher was giving me prose, which I was converting to math notation. I could argue, that this prose→reasoning conversion is not required at training, and can be obtained at inference time with search tools.

Post reply on HN