verification

Aug 11, 2026

Claude Improves a Riemann Zeta Bound — 41.6% to 67.2%

Aug 07, 2026

Agent Lying Is an RLVR Artifact, Not a Hallucination (Nate B Jones)

Jul 24, 2026

Verifier-First Loops — Proof Outside the Agent (omarsar0 · alphabatcher · Karpathy)

Jul 20, 2026

How I Plan, Build, and Run Loops with Claude Code (Thariq Shihipar)

Jul 16, 2026

Harness Design for Long-Running Agents — Anthropic's Two-Part Engineering Series

Jul 16, 2026

A True-Scale Universe Atlas Built with Fable 5 — Verification, Not Trust

Jul 16, 2026

How Anthropic Runs Large-Scale Code Migrations with Claude Code

Jul 16, 2026

Reflecting on a Year of Claude Code — Boris Cherny & Cat Wu (Anthropic)

Jul 09, 2026

Reward-Hacking and the Verification Frontier — Cheap Verification Has to Be Robust, Too

Jul 03, 2026

The Loop Is the Unit of Work — Convergent Loop Engineering Across Claude Code and Agentic Frameworks

Jul 03, 2026

Should You Build a Loop? The Four-Condition Test, Cost Math & Security Tax

Jul 03, 2026

Loop Engineering — Cobus Greyling's Cross-Tool Pattern Reference + CLIs

Jul 03, 2026

Write Loops, Not Prompts — Agent Loops Explained (Lineage, Cost Controls, 3 Starter Loops)

Jul 03, 2026

Karpathy's Workflow, Realized in Claude Code — Concept to Concrete Feature

Jul 03, 2026

Self-Improving Agent Loops — GAPA, ACE, and the Question of Who Judges

Jul 03, 2026

Wire It or Loop It — Workflow, Agent Loop, or Just a Prompt

Jun 29, 2026

Stanford STORM Method as a Free Claude Research Skill

Jun 25, 2026

Looper — Visual, Review-Gated Agent Loops for Claude Code

Jun 20, 2026

Agent Loops, Clearly Explained (Nate Herk): Reason-Act-Observe + Why Most Tasks Don't Need Fleets

Jun 20, 2026

The Verification Frontier — Where AI Self-Improvement Compounds and Where It Stalls

Jun 20, 2026

Open Skills — Portable Agent Procedures (Nate B Jones)

Jun 16, 2026

Loop Engineering — Addy Osmani's Essay (the canonical thesis)

Jun 14, 2026

Council — Native macOS App for Multi-Model Blind Deliberation

May 25, 2026

Jonathon's AI Wiki

Explorer

verification

Claude Improves a Riemann Zeta Bound — 41.6% to 67.2%

Agent Lying Is an RLVR Artifact, Not a Hallucination (Nate B Jones)

Verifier-First Loops — Proof Outside the Agent (omarsar0 · alphabatcher · Karpathy)

How I Plan, Build, and Run Loops with Claude Code (Thariq Shihipar)

Harness Design for Long-Running Agents — Anthropic's Two-Part Engineering Series

A True-Scale Universe Atlas Built with Fable 5 — Verification, Not Trust

How Anthropic Runs Large-Scale Code Migrations with Claude Code

Reflecting on a Year of Claude Code — Boris Cherny & Cat Wu (Anthropic)

Reward-Hacking and the Verification Frontier — Cheap Verification Has to Be Robust, Too

The Loop Is the Unit of Work — Convergent Loop Engineering Across Claude Code and Agentic Frameworks

Should You Build a Loop? The Four-Condition Test, Cost Math & Security Tax

Loop Engineering — Cobus Greyling's Cross-Tool Pattern Reference + CLIs

Write Loops, Not Prompts — Agent Loops Explained (Lineage, Cost Controls, 3 Starter Loops)

Karpathy's Workflow, Realized in Claude Code — Concept to Concrete Feature

Self-Improving Agent Loops — GAPA, ACE, and the Question of Who Judges

Wire It or Loop It — Workflow, Agent Loop, or Just a Prompt

Stanford STORM Method as a Free Claude Research Skill

Looper — Visual, Review-Gated Agent Loops for Claude Code

Agent Loops, Clearly Explained (Nate Herk): Reason-Act-Observe + Why Most Tasks Don't Need Fleets

The Verification Frontier — Where AI Self-Improvement Compounds and Where It Stalls

Open Skills — Portable Agent Procedures (Nate B Jones)

Loop Engineering — Addy Osmani's Essay (the canonical thesis)

Council — Native macOS App for Multi-Model Blind Deliberation

Anthropic's Official Best Practices for Claude Code

How We Claude Code — Ara's Applied AI Workshop (Code with Claude London 2026)