Trading
The trading system: models, guardrails, and what the market teaches.
Eleven days I didn't touch it
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.
Same system, three different traders
Same code, same market, three time periods. One made $964, one lost $217, one's up $321. The difference wasn't the algorithm.
Building David, Not a Smaller Goliath
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 trade three coins, not fifteen
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.
Now the Real Data Starts
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.
What Building a Trading Bot Taught Me About Building Trading Bots
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 House Always Wins. But Retail Can Still Play.
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.
The House Always Wins: Why Retail Crypto Trading Is About to Get a Lot Harder
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.
I wrote the rule. Then I skipped it.
Four days ago I published a blog about a bug I'd nearly shipped. The spec referenced two database fields that did not exist — trade.risk_amount and `trad...
Sprint 120 removed a safety rail. 41 trades later, I got the bill.
By the time I ran the SQL, the number was already there: 41 closed trades since Sprint 120, 24.4% win rate, minus $217 net. Before that month, the system h...
The 10 columns I shipped before touching the multiplier
At 00:56 UTC on 17 April, a trailing stop on XRP-PERP widened from 0.69% to 1.56%. Two-point-three times. The trade took the widened stop, held for 15 hour...
The market is smarter than you. That's the feature.
Sprint 130 added a risk-reward floor: no trade below 2.0:1 post-ATR. Three expert reviewers signed off. The logic was clean, the code was tested, the deplo...
The System Changed Its Mind: What a Directional Flip Looks Like When Its Done Right
Last week SHORTs. This week LONGs. No override. The system detected the regime change and flipped with it.
The Day Nothing Happened Was the Most Important Day
Zero trades in 24 hours. +$134 in 72 hours. Here is why the day the system did nothing was the most important day of the week.
The AI Pricing War Just Got Real: GPT-5.4 vs Claude Opus 4.6 and What It Means for Your Budget
GPT-5.4 launched at $2.50/$15 per million tokens. Claude Opus 4.6 holds at $5/$25. The mid-tier is where the real battle is happening. Here's the pricing landscape every AI builder needs to understand — and why most teams are overpaying.
Every AI Trading Bot Claims Dynamic Regime Detection. Here is What It Actually Looks Like in Production.
Most bots show pnl, not Sharpe. Here is why that matters.
From -23 USD to +1,136 USD: The Sprint 116-125 Era That Fixed Everything
Ten sprints. From a broken system to +1,136 USD profit.
My AI Trading System Did Nothing for 15 Hours. Then It Nailed Two Trades.
15 hours of silence, then two profitable trades in 3 hours. The hardest edge is trusting the system when it is doing nothing.
My AI Trading Bot Treats 4 Coins Equally. Today I Found One Has Been Dragging the Portfolio Down.
SOL has been my weakest coin: 34% WR vs BTC 45%. Per-coin tracking shipping in Sprint 125.