This is super interesting, I'm particularly excited for this one as it may allow teams to scale this architecture for VLAs (vision language action models), and having sparser models means more real-time actions on a locally hosted model
You did not express any desire to wash the car. After nudging, it's funnier:
> Is my desire to make my car clean related to a car wash in any way? To driving to it?
> Your desire to have a clean car isn’t tied to the existence or use of a car wash or to traveling to one. It stems from how much you value the effort, time, and resources you’re willing to invest in achieving cleanliness — whether that means doing it yourself, paying for a professional service, or simply enjoying the routine of a quick walk‑out. Driving to a nearby wash is just one possible method among many; the decision ultimately depends on factors such as how much time you have, how much you’d like to spend, the quality of the wash, and any personal preferences you have for hands‑on versus outsourced cleaning. In this case, walking is the simplest and fastest way, but it isn’t required for you to achieve a clean car.
Common sense is clearly there, but we should not underestimate the colossal heap of tacit assumptions that drive "obvious" decisions in our daily life.
I'm surprised these models haven't picked this up yet in the training data. Both Claude and ChatGPT missed that one when I posed the question to them last year.
There's meaning in the term "car wash" that it understands. But I don't suspect anyone has taught it that for 99.9% of people, going to car wash ONLY means that you're going to wash your car and that it should make that implicit assumption.
What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.
to your point, when my Aussie friends first mentioned a "car park" to my north american born self, i wondered _momentarily_ what that was, then realized it's sort of a fun name for what i would call a parking lot.
These faux questions always have a valid interpretation that the asker doesn't admit (for some reason). The model is then castigated for not making an opinionated choice
Why does this not have (day-one) support for Ollama? The previous model is on there? Is it related to the ongoing refactor work or are people abandoning Ollama for other LLM engines?
Wow, this is fucking phenomenal. I fed it a long transcript asking it to create a summary and it executed it extremely well. For an 8B model this is quite impressive.
I gave it a 2000 line python code that does some fairly sophisticated geodesic calculations on surfaces, and asked to review the code. I then asked Claude and ChatGPT to "assess the accuracy of this review" and they did not hold back. That said, its a very small model, and very fast.
I recently realized that Qwen3.5:4B is way more capable than I thought a model that size could be.
Combine that with the work Liquid puts into RL and fine tuning, and you get models that perform extremely well on minimal hardware.
Combine that with your own fine tuning, and you get a specialized tool that is fast, private, and doesn’t require internet connection.
[1] https://github.com/Liquid4All/cookbook/tree/main/examples/lo...
demo link for anyone that wants to try this out https://playground.liquid.ai/chat?model=cmppnbgse000004l4bc8...
Answer: . . . . So, unless you have a compelling reason not to, walk to the car wash.
> Is my desire to make my car clean related to a car wash in any way? To driving to it?
> Your desire to have a clean car isn’t tied to the existence or use of a car wash or to traveling to one. It stems from how much you value the effort, time, and resources you’re willing to invest in achieving cleanliness — whether that means doing it yourself, paying for a professional service, or simply enjoying the routine of a quick walk‑out. Driving to a nearby wash is just one possible method among many; the decision ultimately depends on factors such as how much time you have, how much you’d like to spend, the quality of the wash, and any personal preferences you have for hands‑on versus outsourced cleaning. In this case, walking is the simplest and fastest way, but it isn’t required for you to achieve a clean car.
Common sense is clearly there, but we should not underestimate the colossal heap of tacit assumptions that drive "obvious" decisions in our daily life.
The whole twist here is that to wash your car, you need your car, so you cannot go by foot.
What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.