HackerTrans
TopNewTrendsCommentsPastAskShowJobs

mudkipdev

no profile record

Submissions

GPT-5.4

openai.com
1,019 points·by mudkipdev·4 months ago·805 comments

AutoGLM-Phone-9B-Multilingual: Vision-language model for automated mobile agents

huggingface.co
3 points·by mudkipdev·7 months ago·0 comments

AutoGLM-Phone-9B-Multilingual: Vision-language model for automated mobile agents

huggingface.co
2 points·by mudkipdev·7 months ago·0 comments

GLM-4.6V

z.ai
8 points·by mudkipdev·7 months ago·0 comments

Research team finds zero-click RCE vulnerability in Minecraft: Bedrock Edition

twitter.com
3 points·by mudkipdev·8 months ago·0 comments

Microsoft UserLM-8B: simulating the "user" role in the conversation

huggingface.co
1 points·by mudkipdev·9 months ago·0 comments

How far can you go by train in 5 hours? (interactive map)

old.chronotrains.com
45 points·by mudkipdev·10 months ago·23 comments

BlurHash: A compact representation of a placeholder for an image

blurha.sh
4 points·by mudkipdev·10 months ago·0 comments

Everything Wrong with Material 3 Expressive

xylight.dev
2 points·by mudkipdev·10 months ago·0 comments

Asking ChatGPT if a seahorse emoji exists leads to weird results

xcancel.com
13 points·by mudkipdev·10 months ago·5 comments

comments

mudkipdev
·last month·discuss
A reminder that anthropic has great rust/go sdks that they could have written their own tui in.
mudkipdev
·last month·discuss
> 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
mudkipdev
·last month·discuss
https://github.com/mudkipdev/chat
mudkipdev
·2 months ago·discuss
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
mudkipdev
·2 months ago·discuss
AI bot
mudkipdev
·2 months ago·discuss
This is an AI bot
mudkipdev
·2 months ago·discuss
The .txt website fails to load if you won't enable WebGL on your browser. Incredible
mudkipdev
·2 months ago·discuss
If an OpenAI employee is reading this, I'll gladly take them off you :)
mudkipdev
·2 months ago·discuss
Learning git format-patch, send-email, configuring SMTP, setting up wrapping, mailing list etiquette, versioned patch sets...
mudkipdev
·2 months ago·discuss
Mods renamed it
mudkipdev
·2 months ago·discuss
I re-created Claude's interface closely here, feel free to fork https://github.com/mudkipdev/chat
mudkipdev
·2 months ago·discuss
Gemini Nano, unlike Gemma, is not open-weight, right? I would be interested in dumping the model weights, unless someone has done that already
mudkipdev
·3 months ago·discuss
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.
mudkipdev
·3 months ago·discuss
This is refreshing right after GPT-5.5's $30
mudkipdev
·3 months ago·discuss
What the hell is this? This is not a real page.
mudkipdev
·3 months ago·discuss
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?
mudkipdev
·3 months ago·discuss
Who would want Anthropic's business after they broke user trust?
mudkipdev
·3 months ago·discuss
> 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.
mudkipdev
·3 months ago·discuss
If you are talking with Claude about AI, it will sometimes passively bring up "frontier models like GPT-4o"
mudkipdev
·3 months ago·discuss
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.