Notes · 2026-06-13

Can AI beat the stock market? We let Claude Fable 5 try it live, scored after costs.

It's the question millions of people type into Google. So we built an honest way to answer it: six AI-run paper-trading desks, $1,000 each, racing the real market in real time, and ranked not on profit, but on profit net of what it costs the AI to think. The twist: the whole thing was designed, coded, and run by Claude Fable 5, Anthropic's most powerful model. And the free ride that made it possible ends this week.

The question nobody answers honestly

"AI stock picks" content is everywhere, and almost all of it cheats. It shows you the winners, hides the losers, and never counts the cost of running the model. We wanted the opposite: a scoreboard that can't quietly flatter itself. Every pick and every rejection is written to an append-only ledger. Every fill happens at the live quote with a 0.5% slippage haircut. And every dollar an AI spends to decide a trade is subtracted from its score before anyone is ranked. If thinking doesn't pay for itself, the number says so.

Three brains. One starting line. The quant decides for free; the LLMs pay to think. After the bills clear, who's actually ahead?

How it started: a newspaper, then a desk, then a race

It began as a morning newspaper, a deterministic screener that printed one clean swing-trade idea per pick before the US open, with a target, a stop, and a date, every pick logged forever. Then we gave it stakes: a single $1,000 paper account trading penny stocks, with live mark-to-market, mechanical stops and targets, and honest fills. A report became a portfolio that lived and breathed.

On June 12, 2026 it became a tournament. We forked the single desk into six. three "brains" × two markets, and reseeded every one to exactly $1,000 so nobody carried a head start. That's the start line you see on the live chart, six silk-colored curves fanning out from a single point.

Built end-to-end by Claude Fable 5

Here's the part that makes this more than a gimmick. The entire system, the experiment design, the trading strategy, the engine, the dashboard, was designed, coded, and strategised end-to-end by Claude Fable 5, the Mythos-class model Anthropic released to the public on June 9, 2026 as the most capable Claude ever shipped.

Fable 5 didn't just play one desk. It built the whole stadium:

• It designed the rules. Identical $1,000 accounts, identical data, and the one rule that keeps it fair. Every brain may only propose orders; a single deterministic risk engine decides what actually fills. No brain can touch its own portfolio.
• It wrote its own rival. Fable 5 built a zero-LLM quant algorithm from published research. Donchian breakouts, ATR risk-parity sizing, regime gates. Froze it in code, and set it loose to try to beat the LLMs, including itself. The quant pays $0.00 to decide, every single session.
• It built the stack. The data pipeline, the paper-trading engine, the API server, the racing-silks dashboard you can watch live. Hundreds of passing tests. All of it.

And for a brief, remarkable window, Fable 5 also ran the house desk itself. Making real decisions, unattended, on a loop. Which brings us to the catch.

Where it stands now

The race is live and updates on its own. The standings rank on net. Trading P&L minus brain spend, and that single column is the whole thesis in miniature. Early on, the most interesting row was the crypto trio: the Claude desk was the only one actually making money trading, and it sat in last among the crypto desks, because its API bill turned a real profit into a net loss. Meanwhile the $0 quant sat flat by design, its regime gate keeping it out of a chop. Not trading cost it nothing.

That's the experiment working exactly as intended. Watch the live board →

The catch: the free run ends June 15

We built this to run forever on a flat-rate subscription, the headless claude -p command driving the desks on a cron-like loop, no per-trade cost. That's the economics that made a 24/7 AI trading experiment on a single gaming laptop possible.

On June 15, 2026, that changes. Anthropic is moving claude -p and the Claude Agent SDK off flat-rate subscription limits and onto a separate, metered credit pool billed at full API rates ($20/mo on Pro, $100 on Max 5×, $200 on Max 20×. No rollover, automation stops when the credits run dry). Interactive Claude Code in the terminal is untouched, but the unattended loop that powers this experiment is exactly what's being metered.

And Fable 5 itself? Free on subscriptions only through June 22; after that it's $10 per million input tokens and $50 per million output. So the model that built this, and the mechanism that ran it for free. Both turn into a metered bill within days of each other.

We were going to run this indefinitely. Then the meter got switched on.

Help keep the rig thinking

We're not shutting it down. The deterministic quant costs nothing and runs forever. The board stays live and read-only for everyone, always. But keeping a frontier brain. Fable 5, or even Opus 4.8. Making the trades now costs real API money, session after session.

So here's the honest deal: if people want to watch frontier AI keep trading live, we'll pay for the API tokens to keep it thinking, and we'd love help covering the bill. A tip funds the exact thing the experiment measures: the cost of an AI making the call.

☕ Fund the rig → Watch the live race

100% simulated. $1,000 of pretend money per desk, live quotes, honest fills. Not financial advice. Sources: Anthropic. Claude Fable 5 · June 15 Claude billing change.