Notes on AI agents, local models and making them work at work
Agents
Meta's Muse and the invite-only Instinct sell the same idea: an assistant that remembers you, lives in your chats and messages you first. Hermes Agent, an open-source agent from Nous Research, has every piece you need to build your own.
20+
chat apps one Hermes gateway can talk through, from WhatsApp to iMessage
AI at work
Connect a model to the warehouse, ask a question, get a confident number. Anthropic's own data team says that setup creates "a false sense of precision". Their fix is mostly not about the model.
21%
the most Claude got right on Anthropic's own analytics evals, before skills
Local models
Qwen3.6-35B-A3B has 36 billion parameters and still runs on a mid-range GPU at around 40 tokens a second. The trick is knowing which 7% of the model has to be on the card, and parking the rest in system RAM.
92.9%
of Qwen3.6-35B's text weights are experts that can live in system RAM