> "Small models" will always outperform as they are deterministic (or closer to it).
Your whole comment feels like, pardon me, like LARPing. No, small models do not outperform the large ones, unless finetuned. Saying that as someone who uses small models 95% vs cloud ones.
> Modern clothing is terrible, plastic filled, hardly resists multiple washings. This isn't the 1990s/2000s anymore where you could buy mid budged solid apparel and keep it forever. The gold existed, up to pre COVID. But since then and the rapid spread of fast fashion collecting cloth wastes is a bad business.
Hard disagree. Live in Central Asia, buy locally produced relatively cheap clothes and they have been lasting years so far.
Ok folks, here is a different perspective. I used local model, GLM-4-0414-32b, a trashy IQ4_XS quant, and here what I got:
prompt #1:
> the car wash only 50 meters from my home. I want to get my car washed, should I drive or walk?
Walking is probably the better option!
Here's why:
Convenience: 50 meters is extremely short – only about 160 feet. You can likely walk there in less than a minute.
Efficiency: Driving involves getting your keys, unlocking the car, starting it, driving 50 meters, parking, locking it again, and then doing the reverse to get home. Walking skips all that.
Environmental Impact: You avoid using fuel for such a short distance.
Exercise: It's a quick little bit of physical activity.
Driving would be overkill for such a short distance. Just walk over!
prompt #2:
> the car wash only 50 meters from my home. I want to get my car washed, should I drive or walk? use long chain of thought thinking
8. Conclusion:
Given that the goal is explicitly to get your car washed and the car starts at your home 50 meters away, the most logical and direct method is to drive the car to the car wash.
Walking does not move the car to the necessary location.
Driving, although a very short distance, is the only method presented that directly facilitates the core task of transporting the car to the wash.
The negligible time difference, minimal environmental impact, and directness make driving the car itself the clear choice for achieving the stated goal.
Therefore, you should drive your car the 50 meters to the car wash.
otoh, nanbeige-3B-Q8 (3 billion weights!) gave right away the following:
Drive.
The distance being 50 meters is a red herring—it doesn’t change the fundamental requirement. You need to move the car, and only driving accomplishes that.
If you meant something different by "drive or walk" (e.g., payment method, DIY vs. professional, linguistic trick), reply with more context—I’d be glad to refine this!
What I relly dislike about these LLM is how verbose they get even for such a short, simple question. Is it really necessary to have such a lobg answer and who's going to read that one anyway?
Maybe it's me and may character but when human gets that verbose for a question that can be answered with "drive, you need the car" I would like to just walk away halfway through the answer to not having to hear all the universes history just to get an answer. /s
The verbosity is likely a result of the system prompt for the LLM telling it to be explanatory in its replies. If the system prompt was set to have the model output shortest final answers, you would likely get the result your way. But then for other questions you would lose benefitting from a deeper explanation. It's a design tradeoff, I believe.
My system prompt is default - "you are a helpful assistant". But that beyound the point though. You don't want too concise outputs as it would degrade the result, unless you are using a reasoning model.
Well, when I asked for a very long answer (prompt #2), the quality had dramatically improved. So yes, longer answer produces better result. At least with small LLMs I can run on my GPU locally.
Depends what you want to achieve; from fundamental educational point of view it is not a good device, too high level; most of the stuff you can build with 555 you can do with standard BJTs, and you'd be able in fact in understand how it works. To me, 555 is good only for dumbed down entertaintment, not true learning.
My semi-tin-foil speculation: The laser research facility is in US (San Diego); Europe is on the brink of a divorce from the US; there is an expectation of scaling down.
Doesn't currently manufacture at commercial scale is not the same as can't make. I don't know what the patent situation is but I assume there are at least a few in the way.
Eminent domain can apply to intellectual property. There is even plenty of US precedent for this in nearly the same circumstances. Then again their need for defensible IP is precisely why ASML would almost certainly never make the partnership you suggest.
Your whole comment feels like, pardon me, like LARPing. No, small models do not outperform the large ones, unless finetuned. Saying that as someone who uses small models 95% vs cloud ones.
reply