@0xLin_i: An intern working as a programmer in Guangzhou built a trading bot with Claude and netted $63,000 on Polymarket — with a median trade size of $7 and an average spread of 2.5%. It's not about a single winning trade; it's repeating that slight 2.5% edge 38,764 times...

X AI KOLs Timeline News

Summary

An intern in Guangzhou built a trading bot using Claude and netted $63,000 on Polymarket through high-frequency small-spread trades, demonstrating the application of AI-assisted quantitative trading in prediction markets.

An intern working as a programmer in Guangzhou built a trading bot with Claude and netted $63,000 on Polymarket. Median trade size: $7. Average spread per trade: a steady 2.5%. It wasn't one big winning trade — it was repeating that tiny 2.5% edge 38,764 times and stacking it up. Three strategies combined: > 1. Use a probability model to scan for undervalued options and place low-price limit orders. > 2. Near the close, if there's still a spread, scoop up the almost-certain winning side as well. > 3. Grab a cheap tail as a bonus, just in case the market suddenly swings wildly. No betting on direction — just eating the pricing gaps that last a few seconds. This is what it looks like when you run a quant system in a prediction market.
Original Article
View Cached Full Text

Cached at: 06/12/26, 03:00 PM

A trainee programmer working in Guangzhou built a trading bot using Claude and netted $63,000 on Polymarket

Median trade size: $7. Average edge per trade: 2.5% stable spread.

No single home-run trade — just a 2.5% edge repeated 38,764 times, stacked up.

Three moves combined:

  1. Use a probability model to find undervalued outcomes, place low-limit orders
  2. Near market close, if a spread still exists, sweep the almost-certain side
  3. Pick up cheap tails — if the market suddenly jolts, they act as a buffer

No directional bet, just feed on that few-seconds pricing gap.

This is what running a quant system in a prediction market looks like.

Similar Articles

@QKBS2002: A junior student at Shanghai Jiao Tong University used Claude to build a trading bot and earned $193,000 on Polymarket. This bot specializes in BTC short-term up/down markets, executes with limit orders, and combines three strategies: arbitrage, market making, and hedging. Breaking it down simply: when it finds a pricing anomaly, it enters and then immediately buys...

X AI KOLs Timeline

A junior student at Shanghai Jiao Tong University used Claude to build a trading bot and earned $193,000 on Polymarket, employing arbitrage, market making, and hedging strategies.

@qkl2058: I did something pretty insane last night: I unleashed Claude and gave it full control of my computer to trade autonomously on Polymarket. Starting capital: just $200. And guess what? In just 10 hours, it turned $200 into $3,000 — a 15x return.

X AI KOLs Timeline

A user claims to have given Claude AI full control of their computer to trade autonomously on the prediction market platform Polymarket, turning $200 into $3,000 in 10 hours — a 15x return — by copying the strategies of high-win-rate traders.

@NXR_NIROX: > A Chinese girl > no quant degree, no Bloomberg terminal, no fund background > just a laptop, opened Claude Code > spent a weekend building a bot for five instruments > mean reversion on indices, breakout on Bitcoin, trend following on commodities > ATR for position sizing, 1% hard stop loss, plus…

X AI KOLs Timeline

A Chinese girl with no quant background used Claude Code over a weekend to create a trading bot covering five instruments, employing mean reversion, breakout, and trend strategies, achieving significant returns, demonstrating the potential of AI tools in automated trading.

@waveking1314: The most thrilling part of this story isn't that he made money. It's that a 29-year-old Chinese salesperson directly used AI to take down an entire quantitative trading team. He was originally just an ordinary salesperson, then quit his job and built an ETH price simulation engine using Claude + 6 AI agents. Last month's profit was $306,000...

X AI KOLs Timeline

A 29-year-old Chinese salesperson built an ETH price simulation engine using Claude and 6 AI agents, earning $306,000 last month, showcasing the potential of AI in quantitative trading.

@cyber_cat7: A former Citadel quant trader was kicked out by his old employer, then rebuilt the entire algorithm using Claude Fable 5 in 48 hours — now, he's made $430,000 through hedge trading on Polymarket. He didn't take a single file. Didn't need to. Ten years of…

X AI KOLs Timeline

A former Citadel quant trader, after being fired, rebuilt the entire trading algorithm using Claude Fable 5 in 48 hours, and through hedge trading on Polymarket, has profited $430,000. The story highlights a probability-based high-frequency trading strategy and the application of the law of large numbers.