Grok-built linear regression bot claims $508K PnL in 125 days on Polymarket
Roger_M_Taylor · x · 2026-10-16
A trader used Grok Bot to build a quant linear regression system for Polymarket's BTC "Up or Down" markets, claiming +$508,183 PnL over 125 days ($4,065/day, $258 per trade, repeating the same setup 33 times per hour).
The multi-agent system works in two steps:
- Linear regression for direction and speed: fit a line through recent BTC/ETH data (slope = Cov(Time, Level) / Var(Time)); positive slope biases long, negative biases short, steeper slope means stronger short-term momentum;
- R² as a cleanliness filter: R² = 1 − SSE/SST decides whether the move is clean enough to trust, avoiding random noise.
The quoted article says Claude was used to analyze over 10 million executions from 10 top Polymarket bots to understand their positioning and inventory management.
The post also promotes the Horizon strategy platform (turning plain-language ideas into backtestable strategies). The PnL numbers are unverified and presented in a marketing context.
More from coding & agent
- ERP•AI launches headless SaaS with $0 seats that bills machines: $1 buys 4,000 record writes — rohanpaul_ai · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16