mudkipdev

FWIW I still run a server for 5 people with 2GB ram and the performance is fine.

A reminder that anthropic has great rust/go sdks that they could have written their own tui in.

The page you have tried to access is not available because the owner of the file you are trying to access has exceeded our short term bandwidth limits. Please try again shortly.

HN hug of death

https://github.com/mudkipdev/chat

Reminds me of the possibility of running DeepSeek at 3-4 t/s with SSD streaming, could be viable if you are running something overnight for example

AI bot

This is an AI bot

The .txt website fails to load if you won't enable WebGL on your browser. Incredible

If an OpenAI employee is reading this, I'll gladly take them off you :)

Learning git format-patch, send-email, configuring SMTP, setting up wrapping, mailing list etiquette, versioned patch sets...

Mods renamed it

I re-created Claude's interface closely here, feel free to fork https://github.com/mudkipdev/chat

Gemini Nano, unlike Gemma, is not open-weight, right? I would be interested in dumping the model weights, unless someone has done that already

I believe the R stood for reasoning, just like OpenAI had their own dedicated o1/o3 family, but now every model just has it built-in.

This is refreshing right after GPT-5.5's $30

What the hell is this? This is not a real page.

This is 3x the price of GPT-5.1, released just 6 months ago. Is no one else alarmed by the trend? What happens when the cheaper models are deprecated/removed over time?

Who would want Anthropic's business after they broke user trust?

Output is too large: Disable unused breakpoints, variants, or colors in your build script.

So instead of using tailwind, which automatically strips unused CSS classes, here you're supposed to manually remove anything you think you might not need by editing lisp code?

Edit: I just took a look at one of the example projects listed, and sure enough it ships a 1 megabyte file called olive.min.css with every possible class:

https://wikimusic.jointhefreeworld.org/css/wikimusic.olive.m...

It's also heavily duplicated, searching for "blur-md" yields 12 entries all with the same definition.

If you are talking with Claude about AI, it will sometimes passively bring up "frontier models like GPT-4o"

HuggingFace has a nice UI where you can save your specs to your account and it will display a checkmark/red X next to every unsloth quantization to estimate if it will fit.

Why is the assumption that they trained for a pelican on a bicycle, rather than running RL for all kinds of 'generate an SVG' tasks?

The GLM coding plan price increased dramatically

I'm getting a "failed to verify your browser" error on this article

Why do you need an API key to tokenize the text? Isn't it supposed to be a cheap step that everything else in the model relies on?

Grayish dark themes are underrated

The Claude prompt is already quite bloated, around 7,000 tokens excluding tools.

If anyone has a better workflow for creating lots of captions in kdenlive please let me know. I had to duplicate each title to the media library and drag it into the timeline, because if I simply copy/pasted then the text content/styling would be shared across instances

Re-read that

Does the large system prompt work fine for this model? If needed, you could use a lightweight CLI like Pi, which only comes with 4 tools by default