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
I really love how fast it is! Their press release comparing it on Strix Halo and M5 Max are impressive. It going twice as fast at GPU benchmarks even more so!
I use it for triaging my messages and emails and reminding me how all of it ties together. It uses Obsidian to know where to put stuff and how to connect information. It isn't perfect. It's very slow (using a 32GB M2 Max) but fast enough for my needs.
A good example of how it's helpful is that it will make certain things relatively frictionless. Like, I need to pay property taxes. I hate this stuff. I got the email reminder from my municipality and it made an entry in my TODOs which points to page with instructions to pay the taxes, including my folio and access numbers for when I log in. That was taken from a document which contains past property tax information. I have it all there, but it compiles relevant data into dedicated TODO pages.
I'm so bad at doing all of this myself. I really don't enjoy it. Send me to buy a carrot at the store and I'll happily walk 30 minutes there and back to do it. It isn't the effort so to speak; it's how unrewarding, inefficient, and bureaucratic it all is. I'm allergic to it.
Sometimes it does a really bad job of making TODOs. Like my wife messaged me about what our dinner plan was, so Qwen went ahead and made a plan for chicken meatball soup based on messages from a week earlier. It totally fabricated the recipe and everything. Yet, I don't know, it was still helpful to be reminded that I'm in charge of dinner.
It's probably best at scaffolding respondes to emails I don't want to send. I will write it, but I appreciate basic information being fleshed out so I can write it without jumping around constantly.
I use it with a custom harness. It could be a lot better. Everything about it could be better. The model is remarkably good for its size and price, though.
Letting Sonnet 4.6 do it instead always yields much better results, much faster, but it's kind of like using a new phone vs a super old one. They can both get you there. The sound quality and camera might be worse, it doesn't look as fancy, but the new one is $1200 and the old one is free on marketplace if you're handy with a screwdriver and a fresh battery. Sounds great to me
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
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.
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?
[1] https://github.com/Liquid4All/cookbook/tree/main/examples/lo...
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.
The question is revealing that the model has a model of language but not of reality. It knows what words go together, but not real-world concepts.
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.
A good example of how it's helpful is that it will make certain things relatively frictionless. Like, I need to pay property taxes. I hate this stuff. I got the email reminder from my municipality and it made an entry in my TODOs which points to page with instructions to pay the taxes, including my folio and access numbers for when I log in. That was taken from a document which contains past property tax information. I have it all there, but it compiles relevant data into dedicated TODO pages.
I'm so bad at doing all of this myself. I really don't enjoy it. Send me to buy a carrot at the store and I'll happily walk 30 minutes there and back to do it. It isn't the effort so to speak; it's how unrewarding, inefficient, and bureaucratic it all is. I'm allergic to it.
Sometimes it does a really bad job of making TODOs. Like my wife messaged me about what our dinner plan was, so Qwen went ahead and made a plan for chicken meatball soup based on messages from a week earlier. It totally fabricated the recipe and everything. Yet, I don't know, it was still helpful to be reminded that I'm in charge of dinner.
It's probably best at scaffolding respondes to emails I don't want to send. I will write it, but I appreciate basic information being fleshed out so I can write it without jumping around constantly.
I use it with a custom harness. It could be a lot better. Everything about it could be better. The model is remarkably good for its size and price, though.
Letting Sonnet 4.6 do it instead always yields much better results, much faster, but it's kind of like using a new phone vs a super old one. They can both get you there. The sound quality and camera might be worse, it doesn't look as fancy, but the new one is $1200 and the old one is free on marketplace if you're handy with a screwdriver and a fresh battery. Sounds great to me
demo link for anyone that wants to try this out https://playground.liquid.ai/chat?model=cmppnbgse000004l4bc8...