<?xml version='1.0' encoding='UTF-8'?>
<rss xmlns:ns0="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>AI Trade Lab · Field Log</title>
    <link>https://bnhous.com/en/blog/</link>
    <ns0:link href="https://bnhous.com/en/blog/feed.xml" rel="self" type="application/rss+xml" />
    <description>Field tests, post-mortems, and AI tool reviews from the AI + crypto trading frontier.</description>
    <language>en</language>
    <lastBuildDate>Thu, 15 May 2026 00:00:00 +0000</lastBuildDate>
    <generator>AI Trade Lab static RSS</generator>
    <item>
      <title>Trading Grok X-Sentiment Signals Lost Us 12% in 3 Months — Honest Postmortem</title>
      <link>https://bnhous.com/en/blog/grok-x-sentiment-trading-loss-case.html</link>
      <guid isPermaLink="true">https://bnhous.com/en/blog/grok-x-sentiment-trading-loss-case.html</guid>
      <pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate>
      <description>We treated Grok as an X crypto KOL sentiment radar and ran 11 entries in 3 months. Net result: -12%. Full postmortem of 3 worst losses, 4 structural traps in KOL sentiment, and how we use Grok now.</description>
    </item>
  <item>
      <title>We Tracked 100 Binance Auto-Invest Trades for 60 Days — What 4 Baskets Showed Us</title>
      <link>https://bnhous.com/en/blog/100-binance-auto-invest-tracking-may-2026.html</link>
      <guid isPermaLink="true">https://bnhous.com/en/blog/100-binance-auto-invest-tracking-may-2026.html</guid>
      <pubDate>Tue, 12 May 2026 00:00:00 +0000</pubDate>
      <description>60 days, 100 real Binance Auto-Invest trades, 4 baskets (BTC, ETH+SOL, Bluechip, AI-Picked). Return distribution, worst 10 trades, and whether AI stock picking beat the passive bluechip basket.</description>
    </item>
    <item>
      <title>AI vs Manual Execution — Same Signals, 30 Days, Two Binance Accounts</title>
      <link>https://bnhous.com/en/blog/ai-vs-manual-trade-30day-backtest.html</link>
      <guid isPermaLink="true">https://bnhous.com/en/blog/ai-vs-manual-trade-30day-backtest.html</guid>
      <pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate>
      <description>Same 14 signals, two Binance accounts: AI semi-auto execution vs human manual. 30 days later, AI won — but only where it should have. Full data + per-signal breakdown.</description>
    </item>
    <item>
      <title>Using AI to Detect Rug Pulls — 3 Case Studies (2 Caught, 1 Missed)</title>
      <link>https://bnhous.com/en/blog/ai-detect-rug-pull-case-study.html</link>
      <guid isPermaLink="true">https://bnhous.com/en/blog/ai-detect-rug-pull-case-study.html</guid>
      <pubDate>Sat, 25 Apr 2026 00:00:00 +0000</pubDate>
      <description>We ran 3 real rug-pull projects through ChatGPT, Claude and Perplexity using only pre-rug public data. 2 were flagged high-risk. 1 slipped through. Here is exactly what AI catches and what it misses.</description>
    </item>
    <item>
      <title>We Ran ChatGPT on BTC Direction 200 Times — Accuracy Distribution + 7 Hallucination Cases</title>
      <link>https://bnhous.com/en/blog/chatgpt-btc-analysis-accuracy-test.html</link>
      <guid isPermaLink="true">https://bnhous.com/en/blog/chatgpt-btc-analysis-accuracy-test.html</guid>
      <pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate>
      <description>Same prompt, 200 runs, ChatGPT as BTC analyst. Direction accuracy, output consistency, hallucination rate — plus 7 red/green hallucination cases. The numbers will disappoint you.</description>
    </item>
    </channel>
</rss>