The Journey

Swapping the two LLMs behind an autonomous trading bot from Opus 4.7 to 4.8, live, without it missing a beat. The trick was replaying 78 real prompts first.

My auth check said healthy for three weeks on a dead credential. The pattern behind it costs more than the bug did.

An audit of 116 instruction files found one stale copy telling twenty repos they were a different project, two files no session has ever read, and 453 lines loaded twice. Here is what to delete from your own CLAUDE.md, and the method that beats judgement.

Same spec, same model, two methods: a seven-part goal prompt against a full agent framework. The lean prompt tied on correctness and won on time, cost, and clutter. Here are the numbers.

Eleven days of unattended trading. Five losing trades, one winner covered them, +$132 net. What the system did right, what drifted, what I fixed on return.

AI can write working code in minutes. The hard part is trusting it without reading every line. Here's what actually makes AI-built code trustworthy.

An AI agent spent an afternoon optimising one of my apps. It tried a change, measured it, kept the one that was genuinely faster, reverted three that weren...

Six AIs told me Graphify uploads your code. I checked by running it, and the actual gotcha is smaller, quieter, and easy to miss.

Claude has a habit of collapsing an open conversation into three multiple-choice options, and once you see why it does it, you can stop it doing it to you.

A field note from researching Graphify: the real privacy model, the honest token numbers, and why I check the source before I publish.

Same code, same market, three time periods. One made $964, one lost $217, one's up $321. The difference wasn't the algorithm.

I built a second brain in 2020 and drowned it in my own output. PARA was the right answer to the wrong era. Here is the shape that fits this one.

How a trading agent reveals the game retail can actually win — by playing where the funds can't or won't go, and learning to love the play.

I checked the XML files BOS-AI used to store 'institutional memory' for thirty agents. Every tag was PLACEHOLDER_X. So I deleted all twelve.

Coinbase lists 15 perp markets. Most alts are leveraged BTC with noise. The case for staying with three, and the one coin I'd seriously paper-test.

I shipped v6 of agent-11 last month. The biggest single change was deletion. The deployed CLAUDE.md went from roughly 250 lines to under 80. The MCP prof...

Seven months of building bought me a system that finally tells the truth about itself. The data those seven months produced is mostly unreadable. The clock just started, and not a moment too soon.

Across 200 trades, the bot was rarely wrong about the market. It was wrong about itself. The dominant failure mode wasn't strategy. It was a system lying to itself about what it was doing.

The first move is to see the game. The second is to refuse to play it on the funds' terms — and find the one you can actually win.

Three forces are converging on retail crypto traders, and none of them favour the small player. The edge isn't intelligence anymore. It's owning the table.