it seems somehow very uncool to comment on the clouds of indifference around the ukraine war, which is now just a collection of live action Call of Duty videoclips. you are supposed to limit yourself to talking about the iPhone Duo hinge issue, not anything real.

"Continuous Integration" is out. What we need now is "Continuous Evolution." A module within my Agent Host that continually scans X for cheaper and faster approaches and then sends me a plan to implement this across my Agent Host which is then approved via GrokBot / Vercel / Cursor.

I didn’t like the design of any of the managed agents I saw anywhere, so I started building my own platform for this. Just for me. It’s easier to do that now than learn <some AI cloud> terminology

One side effect of AI: Personal Vertical Integration I find myself systematically designing my own versions of all the websites I used to use and putting them on my own website. I see no need for Medium, Substack, Facebook. Just build your own and track your own relationships, content, data.

Why stack Mac minis when your agents mostly call APIs? I built an agent host instead: one $24.99/month Hetzner box, an API router, spend caps per agent, and a vault so agents never see a key. How it's built and what it costs:

Autonomous development strategy is far more important than simply "doing the thing." For example - So what if you reverse engineered some old game and ported it to three.js. What is more important is your meta-design. "Create two agents. One that runs the old game and one that runs the new game, then use an old walk through guide on the expected behavior of the game. Click through both the old game and the new game in parallel, find where they diverge, continually iterate the new game until it matches the behavior of the old game." That has nothing to do with programming, its almost entirely some sort of development strategy playbook.

Does your S1 go this hard?

the real "Slop" of modern life is the piles of account logins, interfaces, inboxes, terms & agreements, policies no one reads, spreadsheets, emails, legal agreements, fragmented social networks, constantly outdated code. AI is here to help fight slop with counterslop.

It’s clear to me that agents are going to select and pay for their own APIs, possibly even dynamically manage their own structure and infrastructure to self optimize for cost. The thing that prevents this from happening? Lack of true benchmarking. The agent wants to pick a plugin. There are 20,000 plugins. How does it choose? It needs objective benchmarking of which plugin or API is the most effective for its task. Or it needs objective benchmarking of which internal structure is more performant versus cost. No one is incentivized to provide that data.

The tech formerly known as "crypto" was always about one thing: liquidity flows. Money comes in, stays or leaves. We've run through the waves: Bitcoin libertarians, Ethereum and DePIN infra, NFTs and memecoins, prediction markets, early AI tokens, and now shielding. "The institutions are coming" was supposed to be the next one, but the Clarity Act is turning into a bill only Wall Street banks wanted. The next wave is agents. Money will flow through them, and the most obvious flow is API and infra spend. Right now I pay Cursor, and Cursor runs my agent. That's a middleman. The agent should hold its own wallet and pay Cursor, Anthropic, Vercel or xAI directly for the models, APIs and plugins it uses. No more API key wrangling or marketplace sprawl. It sounds boring, but agent wallets are the real fix. Pair them with shielding and autonomous agent economies get interesting. Crypto produced thousands of very good ideas, and many will come back with agents behind them.

Internet marketing rewarded A/B/C/D multivariate testing. Now agents let you autonomously "fuzz" the entire problem space. Execution seems likely to shift from "stage-gate" to "flood the zone." Unlike multivariate spaghetti throwing, now the spaghetti learns.