markussss
Joined 9 years ago
Joined 9 years ago
[1]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...
The simplest fixes for it is to just insert semicolons yourself, always use const, and not start any lines with [ or (.
This weekend I got an idea to create a 2D-pattern from a 1D initial pattern. I put it on https://ige.land/, and I find it very fun and satisfying to play around with. It's not so elegant and pretty, but it's fun for me, and that's all I was looking for! Click any cell to change that color in the pattern. Right click or long press to set the length of the 1D pattern. It's also fun to first create a pattern and then resize the browser window to see how it looks like.
So, what I'm working on is not really an interesting project or product. I'm working on my creativity, playing with code, and in general having more fun with programming. Making it magical for myself again.
I'm not sure if it's 100% in line with the spirit of the thread, but it's what I'm most excited to be working on! :-)
I refuse to believe that rouge browser extensions and userscripts are such a big problem that Meta decides to invest in security against those attack vectors.
Another thing this website miss out on is that, with goodwill on both parts, Scandinavians can usually communicate with other Scandinavians in different languages. I am Norwegian, and if I meet a Swede, we can just talk with each other. I can't talk Swedish fluently, but I can understand Swedish to such a degree that it's no problem to speak with a Swede who is speaking Swedish.
However, this relationship of understanding languages can be asymmetric, and it's not always as easy for a Swede to understand a Norwegian as it is for a Norwegian to understand a Swede.
Check out this video on asymmetric language understanding from NativLang for more about this! https://www.youtube.com/watch?v=E042GHlUgoQ
My suggestions if you want to further experiment with local models are to use llama.cpp instead of ollama [1], learn a little about the parameters that tune how much VRAM is used [2], look online for jinja template fixes for the model you're testing [3], and choose a model that was designed to do the task you want to achieve, with as high quantization as you can fit. The maximum model size you can run is VRAM + RAM, although you want as little of the model to be in system RAM as possible.
I'm running North Mini Code IQ3_XXS with some tuned parameters to fit my current tasks, and while it is not perfect for everything, it has not failed any tool calls I've asked it to make, or that it figured it should make on its own.
[1]: https://sleepingrobots.com/dreams/stop-using-ollama/
[2]: https://github.com/ggml-org/llama.cpp/blob/master/tools/serv...
[3]: https://gist.github.com/jscott3201/e4b155885cc68c038d6ac8909...