ELO Ratings Questions

ELO Ratings Questions

Author: Noah Gift September 18, 2025 Duration: 3:39

Key Argument

  • Thesis: Using ELO for AI agent evaluation = measuring noise
  • Problem: Wrong evaluators, wrong metrics, wrong assumptions
  • Solution: Quantitative assessment frameworks

The Comparison (00:00-02:00)

Chess ELO

  • FIDE arbiters: 120hr training
  • Binary outcome: win/loss
  • Test-retest: r=0.95
  • Cohen's κ=0.92

AI Agent ELO

  • Random users: Google engineer? CS student? 10-year-old?
  • Undefined dimensions: accuracy? style? speed?
  • Test-retest: r=0.31 (coin flip)
  • Cohen's κ=0.42

Cognitive Bias Cascade (02:00-03:30)

  • Anchoring: 34% rating variance in first 3 seconds
  • Confirmation: 78% selective attention to preferred features
  • Dunning-Kruger: d=1.24 effect size
  • Result: Circular preferences (A>B>C>A)

The Quantitative Alternative (03:30-05:00)

Objective Metrics

  • McCabe complexity ≤20
  • Test coverage ≥80%
  • Big O notation comparison
  • Self-admitted technical debt
  • Reliability: r=0.91 vs r=0.42
  • Effect size: d=2.18

Dream Scenario vs Reality (05:00-06:00)

Dream

  • World's best engineers
  • Annotated metrics
  • Standardized criteria

Reality

  • Random internet users
  • No expertise verification
  • Subjective preferences

Key Statistics

MetricChessAI Agents
Inter-rater reliabilityκ=0.92κ=0.42
Test-retestr=0.95r=0.31
Temporal drift±10 pts±150 pts
Hurst exponent0.890.31

Takeaways

  1. Stop: Using preference votes as quality metrics
  2. Start: Automated complexity analysis
  3. ROI: 4.7 months to break even

Citations Mentioned

  • Kapoor et al. (2025): "AI agents that matter" - κ=0.42 finding
  • Santos et al. (2022): Technical Debt Grading validation
  • Regan & Haworth (2011): Chess arbiter reliability κ=0.92
  • Chapman & Johnson (2002): 34% anchoring effect

Quotable Moments

"You can't rate chess with basketball fans"

"0.31 reliability? That's a coin flip with extra steps"

"Every preference vote is a data crime"

"The psychometrics are screaming"


Resources

  • Technical Debt Grading (TDG) Framework
  • PMAT (Pragmatic AI Labs MCP Agent Toolkit)
  • McCabe Complexity Calculator
  • Cohen's Kappa Calculator

🔥 Hot Course Offers:

🚀 Level Up Your Career:

Learn end-to-end ML engineering from industry veterans at PAIML.COM


Noah Gift guides you through a year-long journey with 52 Weeks of Cloud, a weekly exploration designed for anyone building, managing, or simply curious about modern cloud infrastructure. Each episode digs into a specific technical topic, moving beyond surface-level explanations to offer practical insights you can apply. You’ll hear detailed discussions on the platforms that power the industry-like AWS, Azure, and Google Cloud-and how to navigate multi-cloud strategies effectively. The conversation regularly delves into the orchestration of these systems with Kubernetes and the specialized world of machine learning operations, or MLOps, including the integration and implications of large language models. This isn't just theory; it's a focused look at the tools and methodologies shaping how software is deployed and scaled today. By committing to this podcast, you're essentially getting a structured, expert-led curriculum that breaks down complex subjects into manageable weekly segments, all aimed at building a comprehensive and practical understanding of the cloud ecosystem.
Author: Language: English Episodes: 225

52 Weeks of Cloud
Podcast Episodes
Will Commercial Closed Source LLM Die to SGI and Solaris Unix? [not-audio_url] [/not-audio_url]

Duration: 10:08
Podcast Episode Notes: The Fate of Closed LLMs and the Legacy of Proprietary Unix SystemsSummaryThe episode draws parallels between the decline of proprietary Unix systems (Solaris, SGI) and the potential challenges faci…
OpenAI Red Flags Common to FTX, Theranos, Enron and WeWork [not-audio_url] [/not-audio_url]

Duration: 8:49
Podcast Episode Notes: Red Flags in Tech Fraud – Historical Cases & OpenAISummaryThis episode explores common red flags in high-profile tech fraud cases (Theranos, FTX, Enron) and examines whether similar patterns could…
DeepSeek exposes Americas Monopoly and Oligarchy Problem [not-audio_url] [/not-audio_url]

Duration: 16:51
Podcast Notes & Summary: "Deep-Seek Exposes America's Monopoly Problem"Key Topics DiscussedMonopolies in Big TechStartup Ecosystem ChallengesRegulatory EntrepreneurshipHealthcare & Innovation BarriersGlobal Tech Leadersh…
dual-model-deepseek-coding-workflow [not-audio_url] [/not-audio_url]

Duration: 6:18
Dual Model Context Code Review: A New AI Development WorkflowIntroductionA novel AI-assisted development workflow called dual model context code review challenges traditional approaches like GitHub Copilot by focusing on…
Accelerating GenAI Profit to Zero [not-audio_url] [/not-audio_url]

Duration: 8:11
Accelerating AI "Profit to Zero": Lessons from Open SourceKey ThemesDrawing parallels between open source software (particularly Linux) and the potential future of AI developmentThe role of universities, nonprofits, and…
YAML Inputs to LLMs [not-audio_url] [/not-audio_url]

Duration: 6:19
Natural Language vs Deterministic Interfaces for LLMsKey PointsNatural language interfaces for LLMs are powerful but can be problematic for software engineering and automationBenefits of natural language:Flexible input h…
Deep Seek and LLM Profit to Zero [not-audio_url] [/not-audio_url]

Duration: 8:01
LLM Market Analysis & Future PredictionsMarket DynamicsDeepSeek disrupting LLM space by demonstrating lack of sustainable competitive advantageLM Arena (lm.arena.ai) shows models like Gemini, DeepSeek, Claude frequently…
Context Driven Development [not-audio_url] [/not-audio_url]

Duration: 5:38
Title: Context-Driven Development with AI AssistantsKey Points:Compares context-driven development to DevOps practicesEmphasizes using AI tools for project-wide analysis vs line-by-line assistanceFocuses on feeding entir…
Thoughts on Makefiles [not-audio_url] [/not-audio_url]

Duration: 6:08
Title: The Case for Makefiles in Modern DevelopmentKey Points:Makefiles provide consistency between development and production environmentsPrimary benefit is abstracting complex commands into simple, uniform recipesParti…
Pragmatic AI Labs Platform Updates 12/26/2024 [not-audio_url] [/not-audio_url]

Duration: 3:26
Update 12/26/2024 on the Pragmatic AI Labs Platform development lifecycle. Thanks again for all of the new subscribers. A few things I mention in the video update: Almost every day a new course, lab, or feature will appe…