Right now, if you want to build something like a daemon you will need multiple agents. When a task needs to be delegated, the central control system needs to be able to spin up a few processes and get them going.
You can do this right now. You can create an ensemble of personalities/roles (jr dev, sr dev, project manager) and have them plan.
They do a good job, if you are monitoring it. You can break up the plan into chunks, spin up more instances, distribute chunks and have those instances work on it.
Sadly this cant happen, and I think these are fundamental limits to Generative AI. Right now personas just go ahead and "pretend work" - they say we "I am now going to go and come up with a project plan".
You have a dependency where output from all prompts must be actionable, or verifiable. If output is off, then it snowballs.
This is not a tooling, or context window issue. This is a hard limit to what Generation can achieve. Its impressive that we got this level of emergence, but when you look at output in detail, its flawed.
This is the verification issue, and verification (or disproving something) is the essence of science.
Maybe something can be added to it, or entirely new structures can be built - but generation on its own will not take us over this threshold.
Right now, LLMs are more like actors. They are very good actors, but you dont get your prescriptions from actors.
People will mourn them and there will be real world AI cementeries.
Diffie Whitfield envisioned an internet highway where every computer is connected to every other in 1974 and then went on to find out how to do that communication in secure channels.[1]
I think my vision is quite tame and deductible from the current situation compared to his.
[1] according to Singh Simon: The Code Book
In more democratic countries we'll see lots of suits and court cases over getting access to these agents and assigning intent to your IRL actions based on your 'thoughts' with the AI.
Not a chance will whatever capitalist figures out how to do this allow a measly cultural restriction keep them from pushing that age deep into childhood.
and snitch.
> It'd need to be only personally accessible and safe/private.
IMO there's very little chance that such a thing won't report or sell every conceivable shred of your existence to governments and corporations.