Milad Alizadeh 🍉

llmmenu: Quick LLM Access with Mods and Kitty I use LLMs extensively throughout my day, but I find the workflow of opening a website and starting a new conversation before typing my query to be slow and disruptive. Since I normally prefer keyboar...

New blog post: Quick LLM Access with Mods and Kitty in i3 mil.ad/blog/2025/ll...

inspired by @simonwillison.net 's excellent llm tool

Copy from tmux/nvim to clipboard over SSH Copying text to clipboard when working on a remote machine via SSH can be tricky. While you can usually highlight text with your mouse to copy it to the primary selection clipboard (and paste with mid...

New blog post: How to copy text from tmux/neovim to your local clipboard when working over SSH using OSC-52 escape codes. No more awkward mouse selections! mil.ad/blog/2024/re...

A LinkedIn post, by Yann LeCun (VP & Chief AI Scientist at Meta), which reads: Every institution, library, foundation, cultural group, and government around the world that possesses cultural content should make it available for training ***free and open*** AI foundation models. Free and open AI systems will constitute the repository of all human knowledge and culture. Perhaps someone could draft a new content license to that effect: "you can use our content to train your AI system, but only if you make it freely available with open weights and open source inference code."

Yann LeCun is over on LinkedIn embarrassing himself in new and exciting ways.

It is the white man's burden to train large AI models on ALL the data from museums, libraries, and cultural groups to PRESERVE them.

www.linkedin.com/posts/yann-l...