AMMDI Blyg

No matter how powerful AI agents get, there will always be a need for:

better ways to express intent to them

tools for monitoring and interacting with them

This is an underexplored area

The more capable AI gets, the more this interface becomes the bottleneck and improving it provides value

My dissertation (1996) actually addressed this problem, tangentially. Ahead of my time!

What is the current state-of-the-art?

I'm not sure and need to research it. There must be dozens of agent harness type things that do stuff in this ballpark and I'm not that familiar with them

I should just build one (see PAgents KnowOS etc )

It's difficult to know what to build given how fast things are changing

One obvious approach – build a lot of small, composable components. I'm trying to do this with Hyperphor stack. But I need to rethink in depth (that's what this is for.)

TODO take every bullet item above and sic claude on it, with context