unfortunate name in spanish...

In English, too.

if there is any consolation, this is still up

https://github.com/Jonty/zombocom/

https://welcometozombo.com

> not sure why the whole article assumes the only language in the world is Python

https://github.com/ax-llm/ax (if you're in the typescript world)

can only speak for myself here, but the prompt processing speeds on Apple Sillicon is too slow, especially for any meaningful usage

Discord's embeds for social media links are annoying. TikTok videos show as static images at times. Instagram Reels lose the video entirely and it sends as a thumbnail image. Twitter embeds are hit or miss (or used to be, it has improved).

Embebot automatically detects these links and replies with upgraded versions using services like vxtwitter, vxtiktok, and ddinstagram – which actually embed the video inline with a proper player.

Built on Cloudflare Workers using Durable Objects w/ a SvelteKit dashboard. Server admins can toggle platforms on/off and customize which embed service to use.

  Repo: github.com/callbacked/embebot-cf

This is actually a rewrite to a Cloudflare workers friendly version of my bot since it was written in Go, packaged via Docker and hosted on my homelab, but I've been too busy tending to my homelab and want to host it on more reliable infra.

These demos whether good or bad go in meta's favor I think

Successful demo? sweet! people will rave about it for a bit

Catastrophic failure? sweet! people will still talk about it and for even longer now!

Ali G would have loved this for his ice cream glove idea

Awesome list, any chance of adding OpenRouter? Looking at their website seems like it would be a pain to scrape all of that due to the site's layout.

https://openrouter.ai/docs/api-reference/list-available-mode... OpenRouter has an endpoint to get models and their pricing

Yeah I am going to be adding more sources like that and Groq but just wanted to start with the basics and see if it resonated

30B-A3B works extremely well as a generalist chat model when you pair with scaffolding such as web search. It's fast (for me) using my workstation at home running a 5070 + 128GB of DDR4 3200 RAM @ ~28 tok/s. Love MoE models.

Sadly it falls short during real world coding usage, but fingers crossed that a similarly sized coder variant of Qwen 3 can fill in that gap for me.

This is my script for the Q4_K_XL version from unsloth at 45k context:

llama-server.exe --host 0.0.0.0 --no-webui --alias "Qwen3-30B-A3B-Q4_K_XL" --model "F:\models\unsloth\Qwen3-30B-A3B-128K-GGUF\Qwen3-30B-A3B-128K-UD-Q4_K_XL.gguf" --ctx-size 45000 --n-gpu-layers 99 --slots --metrics --batch-size 2048 --ubatch-size 2048 --temp 0.6 --top-p 0.95 --min-p 0 --presence-penalty 1.5 --repeat-penalty 1.1 --jinja --reasoning-format deepseek --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn --no-mmap --threads 8 --cache-reuse 256 --override-tensor "blk\.([0-9][02468])\.ffn_._exps\.=CPU"