Indeed. [[AI personal assistants 20201011124147]] https://www.zylstra.org/blog/2020/10/narrow-band-digital-personal-assistants/ We should start with the personal here, wrt automation, not the AI to get to quicker results: [[small band AI personal assistant]] where the personal limits the range of possible inputs for a task and the range of acceptable outputs for a task, leaving a smaller area for an AI agent to do its thing in and thus be more effective.

The Rabbit people say their LAM is a new type of foundation model, to be able to deduce user intention and decided on actions. Sounds like the cli tool I tried, but cutting human out of the loop to approve certain steps. Need to see their research what they mean by 'new foundation model'

Rabbit R1 is a personal AI assistant in a retro box. Supposedly without subscription fees, but with access to AI services and with internet connection. Designed to be able to take action (kind of like the promptchaining cli tool I tried out?). Says it has a LAM next to LLM, a 'large action model' which sounds like marketing rather than tech.