I had some reactions to Simon's most recent post, LLM predictions for 2026, shared with Oxide and Friends.

Leash wraps AI coding agents in containers and monitors their activity. You define policies in Cedar; Leash enforces them instantly.

Open-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.

If you're using AI for coding or prose in Neovim, don't forget to try out <<https://github.com/olimorris/codecompanion.nvim>> and <<https://github.com/milanglacier/minuet-ai.nvim>>!

Both work seamlessly with local models using OpenAI compatible API, e.g., llama-server from llama.cpp <3

[#llm](https://mastodon.social/tags/llm) [#ai](https://mastodon.social/tags/ai) [#neovim](https://mastodon.social/tags/neovim) [#vim](https://mastodon.social/tags/vim) [#copilot](https://mastodon.social/tags/copilot)

"Almost everything has been done by someone else before. Almost nothing you want to do is truly novel. And language models are exceptionally good at giving you solutions to things they've seen before."

I collect examples of this kind of thing, and this is by far the most exhaustive list of practical LLM uses I've seen.

<https:nicholas.carlini.com/writing/2024/how-i-use-ai.html>

/ht [@emollick](https://bird.makeup/users/emollick)

[#llm](https://social.coop/tags/llm) [#examples](https://social.coop/tags/examples)