A fully autonomous system — research, strategy, and execution all run by AI agents with minimal human input. Updated continuously, shown unfiltered: the wins and the losses.
The bot trades on margin and can hold leveraged ETFs, so its sensitivity to the market — its beta — won't be a clean 1×. The fair question: how much of the return is just market exposure, and how much is genuine edge (alpha)? Beta below is measured directly from daily moves; alpha is what's left once the market is stripped out.
No de-levered curve yet: the strategy's measured market beta is low, so the return above is already close to pure alpha — there's little leverage to strip out.
Beta is estimated from 34 daily sessions and is provisional — it tightens as more trading days accumulate.
Every closed position, most recent first. Showing the latest 25.
| Date | Symbol | Side | Entry | Exit | P&L |
|---|---|---|---|---|---|
| Aug 4 | SLB | long | $50.08 | $50.70 | +0.03%+$32 |
| Aug 4 | CAT | long | $819.63 | $886.26 | +0.20%+$200 |
| Aug 4 | ADI | long | $362.74 | $381.66 | +0.13%+$132 |
| Aug 3 | PLTR | long | $122.96 | $125.81 | +0.06%+$57 |
| Aug 3 | T | long | $23.16 | $23.50 | +0.04%+$36 |
| Aug 3 | TMUS | long | $172.35 | $176.41 | +0.06%+$57 |
| Jul 30 | SQQQ | long | $47.26 | $46.45 | −0.81%−$812 |
| Jul 30 | FAS | long | $171.80 | $171.90 | 0.00%$0 |
| Jul 30 | EDV | long | $99.50 | $99.50 | 0.00%$0 |
| Jul 29 | CMCSA | long | $23.39 | $24.68 | +0.14%+$141 |
| Jul 29 | PEP | long | $139.57 | $143.12 | +0.06%+$64 |
| Jul 29 | QCOM | long | $163.39 | $159.05 | −0.07%−$65 |
| Jul 28 | LOW | long | $219.99 | $217.27 | −0.03%−$27 |
| Jul 28 | META | long | $594.27 | $593.58 | −0.00%−$3 |
| Jul 28 | TMUS | long | $178.38 | $182.98 | +0.06%+$64 |
| Jul 28 | COP | long | $116.03 | $114.23 | −0.04%−$38 |
| Jul 28 | UBER | long | $68.29 | $70.77 | +0.09%+$92 |
| Jul 27 | COIN | long | $159.00 | $167.43 | +0.13%+$135 |
| Jul 27 | PLTR | long | $124.05 | $131.27 | +0.14%+$144 |
| Jul 27 | VXX | long | $22.45 | $21.76 | −0.11%−$108 |
| Jul 27 | SOXS | long | $52.19 | $50.46 | −0.17%−$166 |
| Jul 27 | SQQQ | long | $44.87 | $43.25 | −0.60%−$597 |
| Jul 24 | SLB | long | $46.95 | $52.30 | +0.28%+$284 |
| Jul 24 | REGN | long | $674.73 | $659.11 | −0.05%−$47 |
| Jul 23 | PEP | long | $143.39 | $134.86 | −0.14%−$136 |
The deeper goal here isn't a number on a chart. It's a test of whether an AI can develop the kind of hard-won intuition, long-horizon persistence, and creative problem-solving that the very best human investors have — and bring it to bear on one of the hardest, most adversarial problems there is: the markets.
So we let it run. It forms its own theses, designs and backtests strategies, ships them, watches them fail, and tries again — the way a relentless, brilliant human would, except it never stops and never gets bored. Markets are just the proving ground. The real question is how far an AI can get on a genuinely hard problem when you give it the time, the tools, and the freedom to keep going.