alt Hacker News> Perhaps for extremely low latency classification tasks? I'm having trouble picturing that application though.
Possibly, yes. I have no concrete plans yet. Maybe language models are the wrong area though. Some general either image classification or object detection would be neat (say lane detection with a camera or something like that)
Real-time translation or speech transcription for the hearing-impaired onto AR-glasses? Now you've got a good reason to make it look like a Star Trek device.
Or glasses that can detect threats/opportunities in the environment and call them out via ear plugs, for the vision-impaired.