WinstonSmith84
Joined 6 years ago
Joined 6 years ago
But if you don't do any agentic work, Herdr has 0 value vs. tmux.
Anyway, the best comment I could find is that one here where even the main dev doesn't know the direction .. https://github.com/herdrdev/herdr-app/issues/63#issuecomment...
Lack of vision and fragmentation is concerning
Or, you have Spanish people who start their dinner at 10PM while Germans living in the same timezone are already sleeping at that time...
With that said, I don't know where you live nor what is your situation, and like I said previously many people can dictate how their day shall look like but of course not everybody can.
You think about a frontal attack like in Ukraine, and maybe you're right. But Russia is already waging a much more subtle war against NATO. Look at who's leading the US. Look at Brexit. Or look at who could soon lead France or Germany... Their conventional army may be weak, but they don't need to fire a bullet either.
- economy has been slowing down (the real one, the people) while stocks are at record high
- a long overdue business cycle which has been pushed back and back and back ...
- rates hiking (in a slowing down economy)
- bubbles, and that AI bubble is huge. Loving AI on an every day basis but revenue wise, it's not mainstream, far from it. Average people want free stuff, they're good with Google or Facebook throwing them ads, they don't want to pay $200 for a subscription and fact is, 2026 revenues are about $100b totall. Meanwhile hyperscalers are spending about $1 to $2 trillion alone in 2026, and meant to increase within the next few years. You need a lot of imagination to see how this can "flatten" nicely.
Like internet didn't disappear after 2001, AI is here to stay, too. But...
And yes, they will be acquired by a company which will have survived the next crash at a fraction of their currently estimated valuation and we will truly have the next ride of the economy .. many years ahead if 2001 is an example.
1. Launching workflows, so it avoids some large configuration
2. Reviewing work, with reviewers restricted to read-only tools or specific tools. Or some tools for reviewers to check hashes, correctness, etc.
3. I'm using the widely used pi-extensible-workflows. So say you want to stop a workflow, you gonna call workflow_stop. Or check the status with workflow_status. Without Codemode, Pi exposes an API, that the agent can use. So yes, you can call workflow_status. Or call workflow_stop. With Codemode, the agent can do something more complex like a for loop over all the list of workflow ids and get a status and stop them all (again, it's just an example).
So basically, Codemode allows to build a sort of framework for more correctness like using a typed language vs. JavaScript without a linter. It gives boundaries essentially. And also Codemode allows an agent to do things more easily like using internal Pi extensions.