avasan

That makes this all the more impressive!! What happens when you get an incorrect interpretation though? That is now in the "previous context bucket". Assuming the user addresses the issue through the LLM layer by talking to through it, do you think that the subsequent interactions could compound the error?

I sometimes face issues with LLMs running out of tokens or only using partial contacts from previous conversations - thereby repeating or compounding on previous incorrect responses.

Any thoughts on how to tackle that? Or is that too abstract a problem/beyond the scope to address at the moment?

If you don't start from a clean-slate, does the behavior change drastically? Does the interaction between the LLM layer and the MCP/ROS become more efficient if it already has some context? Would that be something you'd want to toggle or do previous conversation contexts cause issues with new command implementations?

LLMs sometimes hallucinate while stating one thing and outputting disconnected commands/code on the back end in many superficial/general models (Claude included) - does the MCP try to correct/account for that? Or is user oversight necessary to ensure that actions match the LLM output? Is the only way to stop aberrant operation by hitting a physical emergency stop or can the LLM interface be used to for that?

This looks like very exciting work! I'm curious - how much pre-context did you need to provide Claude to operate the industrial robot? That looks like a very complex environment.

Is the visual quality really boosted? It seems to give a very distinctive, almost uncanny-valley look to the video.

But the upscaling isn't applied live/on viewing, right? The video being upscaled is still stored on their server and then streamed. How does it reduce storage costs?