Root Two

have been working on my own subagent harness so i can use subagents with different providers from within claude code, been working well in my own workflows looking for beta testers & contributors to take it for a spin before i make it public

there's a principle in game theory simulations where beginning cooperatively and maintaining a cooperative stance until several betrayals produces optimal outcomes for all agents. this really changed my understanding of both how to interact with people and how to understand how an alien intelligence would behave

it's strange to see the world of the past fade before my eyes from 2012 through 2024, I wrote code in long sessions of sitting in vim -- sometimes typing, mostly thinking, flipping between different terminals, making changes, looking at errors, googling, reading stackoverflow... I took pride in carrying in my head these towering abstractions. I knew every nook and cranny of my business logic, like a neighborhood you live in. I felt extra fast when tab-completing a single long variable name. Nice. I placed every parenthesis, every semicolon, myself. Hundreds of thousands of them. And like a great wave washing over your sandcastle on the beach, it is now all gone. Engineering will never again be as it once was. What's especially significant about it to me is that there's barely a record of the way it was: I've spent thousands of hours writing software, and I don't think there's a single video recording of me doing it. I remember how it was: the long breaks of meditative silence, the frustration of hunting a particularly tricky bug, the relief and joy in solving it, the expressions of taste and cleverness that come with any manual craft. But it's hard to communicate how it was to someone who has never experienced it. As with all histories, the narrative is lacking in depth: you really had to be there.

One of the bigger misconceptions in trading is that you need an informational edge, some insight, some pattern, some signal that others haven't found. If that's the game you're playing, you're competing against people with more data, more compute, and more capital than you'll ever have. You are not in that game, and pretending otherwise is the first mistake. The edge that's actually within reach looks nothing like that. It's (for the most part) doing what other people refuse to do, sitting in discomfort, absorbing volatility, providing liquidity to the person who simply wants out. You're not outsmarting anyone in a direct sense, but instead you're out-tolerating them. That's a less exciting framing, but it's a more honest one. The secret sauce most traders are searching for definitely exists somewhere, and they probably still couldn't execute it consistently even if they found it. The better question isn't what do I know that others don't, but what can I do that others won't.

I still like trading, but I do miss the days of occasional phone turret violence.