reaslonik

From the blog page at https://blog.mozilla.org/en/firefox/ai-window/

it looks like it's an explicit option to open a window with AI features and without, so you get a choice to enable the features if you want them

Of course, it's generally useful for things you can verify, which for acronyms is easy as long as you find the words

At least with their previous features it's been possible to set the address to any custom services you may have running, remote or local. For example Against all expectations I had I've actually found the highlight -> explain tool to be useful when sent to my local vLLM instance with a template I like.

Why not google/ddg/bing etc. them? That's on the context menu too, but LLMs seem uniquely suited at some problems like acronyms that are shared across many fields but different meanings, highlighting a sentence turns out the right acronyms very fast where search engines would take several attempts and is what I used to do previously.

One thing I find that constantly makes pain for users is assuming that any of these models are thinking, when in reality they're completing a sentence. This might seem like a nitpick at first, but it's a huge deal in reality: if you ask a language model to evaluate whether a solution is right, it's not evaluating the solution, it's giving you a statistically likely next sentence where yes and no are fairly common. If you tell it's wrong, the likely next sentence is something affirming it, but it doesen't really make a difference.

The only way to use a tool like this is to give a problem that fits context, evaluate the solution it chugs at you and re-roll it if it wasn't correct. Don't tell a language model to think because it can't and won't. It's a way less efficient way of re-rolling the solution

I'm running the huggingface's .safetensors with vLLM with as little starting parameters as possible. I thought it must not be sending temp right, but after setting temp to something else I got chinese so it should be sending it.

Overall if you're memory constrained it's probably still worth to try and fiddle around with it if you can get it to work. Speedwise if you got the memory a 5090 can get ~50-100tok/s for a single query with 32B-AWQ and way more if you have something parallel like open-webui

Breaks as in contains words that grammatically work but don't make sense, mistakes the symbol | for a person, points back to things that didn't exist in the request etc. I use templates like these for explaining questions:

from

```

excerpt of text or code from some application or site

```

What is the meaning of excerpt?

Just doesen't seem to work at a useable level. Coding questions get code that runs, but almost always misses so many things that finding out what it missed and fixing those takes a lot more time than handwriting code.

>Overall it still seems extremely good for its size and I wouldn't expect anything below 30B to behave like that. I mean, it flies with 100 tok/sec even on a 1650 :D

For it's size absolutely, I've not seen 1,5B models that form even sentences right most of the time so this is miles ahead of most small models, not just to the hinted at levels the benchmarks would you have believe

While impressive that the output isn't completely undecipherable, my real-world queries for SpringBoot project with most popular libraries don't compare so favorably to their benchmarks against Qwen3 32B, which I also run regularly (a 4bit quantized version of). Explaining tasks break completely and often.

Used their recommended temperature, top_k, top_p and so on settings

You need to leave much more room for context if you want to do useful work besides entertainment. Luckily there are _several_ PCIe slots on a motherboard. New Nvidia cards at retail(or above) are not the only choice for building a cluster; I threw a pile of Intel Battlemage cards on it and got away with ~30% of the nvidia cost for same capacity (setup was _not_ easy in early 2025 though).

You can gain a lot of performance by using optimal quantization techniques for your setup(ix, awq etc), different llamacpp builds do different between each other and very different compared to something like vLLM

>I can do whatever the hell I want from this M1 MBA in a hotel room in Japan.

As long as it's within terms and conditions of whatever agreement you made for that $20. I can run queries on my own inference setup from remote locations too