Загрузка видео...

Не удалось загрузить видео

На главную

It worked. Gave Claude $20. Left it coding overnight. Woke up to: • finished script • +$95 from first 5 trades Didn’t touch anything. Then I found this wallet: 0xb27b...b82 • $384,858 profit • 13,070 predictions • $18.5K biggest win • Started March 2026 Almost no one is watching...

72,779 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

An ex-Anthropic engineer leaked something at a party he was not supposed to share. SF rooftop. I mentioned running trading agents on Claude. He stopped mid-conversation. You are doing it wrong. Everyone is. Claude is a runtime. Not a chatbox. You pair it with repos. He opened one GitHub link on his phone: github/anthropic-cookbook 14,000 stars. Every workflow pattern they built internally before public release. Agents. Tool use. Evals. Citations. Full architecture exposed. Most people type prompts. That is not how we use it. You connect Claude to a codebase. It reads the structure. Understands context. Builds on top of existing logic. I left at 2AM and connected Claude Code to poly_data. 86 million Polymarket trades. Every wallet. Every entry. Every signal. Claude did not guess. It read the dataset and built detection layers. Week 1: +$1,400 Week 2: +$3,800 Current: +$9,100 4 agents running. 74% win rate. His team operates with a floor of PhDs and $800M AUM. My setup: Claude + VPS. $25 per month. Repos are free. I asked what separates his firm from retail traders. Keyboard shortcuts and repo structure. That is it. The model is identical for everyone. He texted 2 days later: Delete everything I told you. Too late. The edge is not the AI. It is how you connect it to structured data and let it build detection systems autonomously. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "money" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Connect Claude to your data this week. Start with small datasets. Scale on evidence.

Himanshu Kumar

12,519 просмотров • 14 часов назад

THIS WALLET STACKED $230K ON BTC UP/DOWN BETS. THE BLUEPRINT TO AUTOMATE THE SAME EDGE WITH CLAUDE The wallet is $230K all-time, every position a Bitcoin or Ethereum Up or Down market It never guesses direction. It enters only when the math and the market disagree THE STRATEGY: BTC moves are not fully random. When the market enters a committed directional state, continuation is measurable. That is Markov persistence Entry signal: > Δ = p̂ − q ≥ ε Model probability minus market price. Enter only on a 5% gap or more Persistence filter: > p(j*,j*) ≥ 0.87 Only trade states with 0.87 persistence or higher. Below that, skip. This is what holds the win rate above 65% with zero directional guessing Payout: > r = (1 − q) / q At q = 0.647 that is +54.5% a win. At q = 0.441, +126.7%. Lower entry price, bigger asymmetry Sizing: > f* = p − (1−p)/b Kelly. At p = 0.87, b = 0.647, f* ≈ 0.71. Size to the edge, never to gut HOW TO BUILD IT WITH CLAUDE: What separates this from a static bot: Claude reads its own trade journal every night and rewrites its own thresholds 1. Take an open-source Polymarket bot repo as your base logic. Feed it to Claude and have it migrate to CLOB v2: py_clob_client_v2, Safe wallet support, fee-aware evaluation 2. Hard-code the filters. Enter only when Δ ≥ 0.05 and p(j*,j*) ≥ 0.87. Apply Kelly on every fill. 3. Run DRY_RUN first. Log every signal, entry price, Markov state, and simulated P/L. No real money until the numbers hold for days 4. The nightly loop. Claude reads the journal, finds which persistence states actually won, adjusts MIN_PROB and MIN_EDGE, ships tomorrow's rules. The agent is sharper after 50 to 100 trades THE SETUP: Claude Opus as the brain. An open-source repo as the starting logic. A Polygon wallet with $50 to $100. Telegram for the morning report Start at $1 to $2 per trade while it learns. Scale only when the dry runs and the live fills line up 17,000 trades compound a thin edge into six figures. The model finds the edge. The nightly loop keeps it sharp Bookmark before you point a bot at your first window

Yarchi

22,871 просмотров • 1 месяц назад