I tried actually talking to it. It reminded me of GPT-2.
VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
191–200 of 226 posts
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#192Earlier quoted context omitted.
How would it know about Wikipedia and when to use it? From the tool description? If we had 100k such tools, then that wouldn't even fit in the context. This is only one example, plus if the topic is more complex, maybe it had to search/learn everything (what is table tennis, what is spin, what is a human, what is a ball), etc. So it would be like spawning a baby human, have it spend an (instant) life learning about t…
Imagine you only know how to cook (use fry pan skill) and know how to cook omelette (recipe). You get the task to cook doner kebab. How many Wikipedia pages do you need to read to get a good understanding? I guess its max 5. I think grounding your abstract problem to an example makes it more trivial, than it sounds in general. > How would it know about Wikipedia and when to use it? 2 general concepts "You have to get…
>Doner kebab or döner kebab[a] is a Turkish
(what is turkish)->(parse lots of potentially relevant/irrelevant context because I have no way of knowing which if any of this informs the doner kebab before I've looked at it)
>dish made of meat
(what is meat) -> (parse lots of potentially ir/relevant context because I don't know if the specific origin/chemistry/mechanics or whether maillard reactions are important before I learn about them)
>cooked on a vertical rotisserie.
(what is a rotisserie) -> etc etc etc
Seems significantly less efficient than just having the various (how to cook > meat, tools > rotisserie, how to cook > seasoning > tomato; lettuce; cabbage; onion with sumac; fresh or pickled cucumber or chili; various sauces, etc) just already built in to the weights.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#193Earlier quoted context omitted.
Imagine you only know how to cook (use fry pan skill) and know how to cook omelette (recipe). You get the task to cook doner kebab. How many Wikipedia pages do you need to read to get a good understanding? I guess its max 5. I think grounding your abstract problem to an example makes it more trivial, than it sounds in general. > How would it know about Wikipedia and when to use it? 2 general concepts "You have to get…
I'm just playing devil's advocate here. Yes, but still "how to cook" is not atomic. It involves knowing how to move stuff, how to measure, what "cooked" looks like in different environment (i.e. different lighting) or variations in ingredients, how to recover from specific failures (i.e. a good cook can fix accidentally adding too much salt, by counter-balancing with an ingredient that absorbs the extra salt). And th…
Just boiling water would be difficult. Do I just add heat until I see bubbles? Or should I have a world model in which I understand that boiling water will be of varying temperatures at varying altitudes and given different liquids.
Because if the recipe just says "boil for 10 minutes" but the thing being cooked really needs a temperature of 212F for 10 minutes, the thing isn't going to be cooked if you're not actually at 212 for 10.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#194I don't get this beating opus, It just hardcoded the tasks for bench , It does even respond normally
A alot randomness in it
Please don't hype
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#195Am 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…
Sure it is small, 3B. But on Pi Zero, I can tell you from my experience, you'll be disappointed.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#196Am 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…
I have been obsessed with the idea of this for a while, theres a Qwen with Opus reasoning distilled that works nicely as well. I think the next frontier is optimizing the models to be more capable on less hardware especially if it can learn on the fly.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#197I have been thinking about how to use this. Since it doesn’t support tool calling I have been considering a dual model deployment, where a small tool calling llm drives the majority of the user experience, and vibe thinker is tapped for reasoning by the other llm. So who has suggestions on small models with excellent tool calling capabilities?
Qwen3.6-35B-A3B is pretty amazing. I'm using it with 96k context on 24GB VRAM through ollama.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#198Beats Opus 4.5 on reasoning you say? Prompt: If A goes to B who then goes to C, can A send something to C? Response: We need to interpret best. The phrase "If A goes to B who then goes to C, can A send something to C?" could be a puzzle about the concept of sending something (like passing a ball) and the relationships. Scenario: A gives something to B, and B passes it on to C. Question: Can A also give the same thing…
If A goes to B who then goes to C does C know A?
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#199I gave this a run on llama.cpp locally. My GPU is Ge1080, so I needed quantized version for even such a small model and…
This. Is. Amazing. I am flabbergasted.
I am not into the whole GenAI thing and I have very little need for anything agentic, but Python, C++ and Maths is exactly what I mostly used these for, so this might actually become my main work horse. This is so cool.
I even used it for stuff it is not built for, asking complex qustion on history (Battle of Tours 732) and literature (Joyce’s Portrait of Artist) and it was surprisingly good, even though it started to hallucinate names and details (such as claiming Joyce’s father was a priest). For 3B I expected it to mainly spout complete nonsense.
Re: VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
#200Man just need something like this with tool calling.