🤖 Bring your own AI models to @code!
Connect models from providers you already use, run local models, and choose the right model for every workflow in VS Code.
📖 Read the full post: aka.ms/vscode/blog/by…
English
Post
@code I need the same but in VS Community, please share some love here too
English
Still in beta, Polymarket already has best-in-class liquidity across virtually every category: pregame, futures, even in-play tennis. The depth is honestly absurd.
Deposit $20, get free $50 with my code DOV50
Try trading on tonight’s game 👇
English
@code I used the opencode go in vs code, but when I attached a picture, it showed an error.
English
@code Anyone make it work with local Ollama models like Gemma4?
English
@code . @Microsoft could host some open weight models too and provide them to the users. You will not loose anything, and only gain user base and usage that you can use to train your next models on.
English
@code It would be nice, if we could configure VS Code to be fully air gapped and to use a local instruction model for autocompletion too. But it is nice, that we can use local models at least for some tasks.
English
@code Nice. Direct API key support for multiple providers plus local via Ollama in the new models panel.
English
@code Breaking:
Gerard Sans | Axiom 🇬🇧@gerardsans
🚨 Claude Mythos Jailbreak: from LLM to Agentic OS. Anthropic leak revealed: • Computer use, file system & network • Agentic loop primitives • Self-optimisation Official guide confirms: long-horizon, code review/debug & workflow orchestration. OS > Harness > Weights More:
English
@code Extremely handy. Turns Github Copilot into my harness of choice
English
@code Token caching seems non-existent with BYOM and AI Foundry. Costs $$$.
English
