I can think of many uses for this thing, robotics being one that could really benefit from something like this. A hybrid approach with this and action models and vllms could be really good mix, also agents inside simulated virtual environments, etc... basically anywhere where latency is important but you need some intelligence this will fill those gaps. Weave it with other systems and you have a nervous system as jev with other models like vllm or even text as the slower deeper thinker.
Yeah. Computer use is essentially a model navigating the OS-provided accessibility tree. I imagine a model trained on it would operate the computer exactly as we saw it control Doom.
Coincidentally, the midnight theme was created specifically for the reason you asked this question: for using HN while lying down next to a toddler/partner. It has a reduced white point because most dark modes are too bright to use in bed near others. Def not a great daytime dark theme though – that's what the others are for :)
Yeah, all possible, the infra for all of that is set up. I think I understand your request but can u send me an email so I can talk it through with you a little more?
OpenAI has been teasing how fast computer use is with their models running on Cerebras chips but the difference here is a burning hole in your pocket.
reply