• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.

A 70.8 on Terminal-Bench 2.1 puts LongCat-2.0 in serious contention for agentic coding work, and the free week is a real window to evaluate it against an existing stack. Million-token context also changes what whole-repo passes are affordable.

• postHermes profiles are now portable and shareable: Run /export to save a profile as
• postHermes has twelve browser tools. Browser Use mode replaces them with a single on
• postHermes now has an optional skill for tldraw offline, @tldraw's desktop whiteboar
• postNew in Hermes Agent: a credential firewall for Docker sandboxes. Your real keys

• postIntroducing Muse Code (beta), a terminal coding agent built for long-horizon sofAIatMeta
• articleQwen3-Coder: Agentic Coding in the WorldQwen Team
• videoStop babysitting your agents... — Brandon Waselnuk, UnblockedAI Engineer

Sign in to comment.

Loading comments…