<?xml version="1.0" encoding="UTF-8"?>
<oembed>
  <version>1.0</version>
  <type>link</type>
  <title>Correlated Errors in Large Language Models (arXiv:2506.07962 · ICML 2025) — Fresh Preprint for CFO &amp; Quant Professional Upskilling | MARKOWITZ.SYSTEMS</title>
  <description>Fresh continuing professional education preprint: Elliot Kim, Avi Garg, Kenny Peng &amp; Nikhil Garg (Cornell Tech) (2025, arXiv:2506.07962 · ICML 2025). Formula: P(Model_A wrong ∧ Model_B wrong | Model_B wrong) ≈ 0.45–0.60  ≫  p_err. Actionable upskilling: Never assume multi-agent ensembles or LLM-as-a-Judge diversify risk without empirically measuring off-diagonal error covariance Σ on your own ledger and contract data.. Full library: https://markowitz.systems/preprints</description>
  <author_name>MARKOWITZ.SYSTEMS Quantitative Finance &amp; Continuing Professional Education Collective</author_name>
  <author_url>https://markowitz.systems/education</author_url>
  <provider_name>MARKOWITZ.SYSTEMS — Fresh AI Preprints &amp; Professional Upskilling</provider_name>
  <provider_url>https://markowitz.systems</provider_url>
  <cache_age>86400</cache_age>
  <thumbnail_url>https://markowitz.systems/og-card.png</thumbnail_url>
  <thumbnail_width>1200</thumbnail_width>
  <thumbnail_height>630</thumbnail_height>
  <url>https://markowitz.systems/preprint/pp-01</url>
</oembed>