Have you found a good way to manage multiple agents though, even via Rex?

I use the supermatt skills a lot in a issue-based workflow. It's /orchestrate skill is quite good and you can just tell it to use Rex instead of Herdr. Also with Rex I just always have one session open with an agent that i tell to "look how far the other sessions are progressing, or to look if anything needs any input from me and if so present me all the decision and things that need me in a site you create for that purpose. explain it intuitively without assuming prior knowledge. a site where i can export my choices and commentary to json so i can send it back to you" or something like this

Other countries are cracking down which makes desire to migrate less.

Yes, especially if you running a multi-node setup. I'm still running on HashiCorp Nomad.

Exceptional results come from the things that people do when no one is looking.

Can anyone recommend something self-hosted that does this?

Why isn't a LLM as smart as a human? Therein lies your problem.

A calculator used to be a human job. Are calculators smarter than humans?

I'm asking why is it reassuring about his job? Surely your big human brain can understand to be automated away doesn't mean the machine is "smart as a human" whatever that means. There is probably not a lot of utility in comparing synthetic and organic intelligence from such a reductive perspective.

Factory workers got automated by machines. Is a robotic arm smarter than a human? Is a tractor smarter than a bovine?

My question is simply what is he doing that is so "smart" or novel that it cannot be automated or mechanized. This should not be so hard to understand.

> My question is simply

Why should they answer the question if you can't answer it yourself? What is he doing that is so "smart" or novel that it cannot be automated or mechanized right now? If you knew that answer you could put every one out of a job right now and you would be counting your trillions instead of asking "simple" questions on HN

Factory workers that did repetitive things that didn't require any thinking got automated away by machines. But there are still factory workers today that do things that require thinking.

Machines don't go deep on problems, humans do. A machine has no will or purpose to solve a novel problem on their own. Hope that answers your question.

It doesn't need will? Voyager has gotten farther than likely any human will ever reach. It doesn't have will. How did it happen? Because human will is not the only animus in the universe.

How are these math problems being solved? AI just needs to recursively self prompt. Why does it need a human will? As long as the power keeps flowing and the recursion is resilient, what computational problem discoverable by a human is out of reach?

Technical skills are very much still required to take the product into maturity. Coding a prototype is very different from building something actually polished enough to generate value.

No, there's a class of apps that are very much small enough to not require them, yet still deliver value. You're thinking too large.

Why did you guys migrate away from Nomad?

Short answer is GitOps. Other reasons include ghost services in nomad, random CSI volume lock-ups (which might just be AWS's fault), lack of deployment options for self-hosting 3rd party applications. K8s Helm charts are available for everything and ArgoCD visibility with SSO makes everything easy to see.

Most people are not like you and don’t care about this. They just want something that works.

I was going to add the same sentiment with the addendum that normal people seem to find AI really useful, and long for Siri to be a more useful companion. Apple makes a compelling argument of an agent with frontier level smarts, access to your Apple stuff like iMessage, Reminder and Mail, and privacy (which I'm not here to debate how they're handling). Normal people like it, and Siri getting better is an advantage.

Are we able to use CUA to build a system similar to Grok Bot?

It's a specialized classifier for actions on a form. So.. not totally. If you are building a bot system, which can fill form quickly without having to reason too much about the form, this probably can help.