methodology

• Jul 31, 2026
  The Virtues of Typed Reasoning
• Jul 30, 2026
  Borrowed Vocabulary for the Hypothesis Edge
• Jul 19, 2026
  Assurance at the Boundary: The Level Below AAL-1
• Jul 11, 2026
  Hiring Is Evals
• Jul 10, 2026
  How to Audit a Benchmark
• Jul 06, 2026
  Nodewise E-Values Under Graph Interference: Causal Abuse Filtering for Agent Platforms
• Jul 06, 2026
  Regeneration Re-Prices Contamination
• Jul 05, 2026
  Union-Find Compaction: Provenance-Preserving Context Compression for LLM Agents
• Jun 22, 2026
  Detecting and Refining Ambiguous Specifications, Automatically (DRAFT)
• Jun 08, 2026
  How Not to Run SWE-bench Pro
• May 28, 2026
  The Hypothesis Graph: A Verifiable Semantic Memory for Coding Agents
• May 24, 2026
  Red-Teaming Human-Likeness
• May 08, 2026
  Sweep & Triage
• May 07, 2026
  Investigate
• May 04, 2026
  Abduction
• May 04, 2026
  Modes of Reason
• Apr 29, 2026
  Before You Compose
• Apr 28, 2026
  The Hypothesis Graph
• Apr 14, 2026
  Prework
• Apr 14, 2026
  The Prereg Checklist
• Apr 13, 2026
  Bug Hunt
• Apr 11, 2026
  ephemeral IRC
• Apr 10, 2026
  Revised SOAP Notes: Soar
• Apr 06, 2026
  New Reading
• Apr 05, 2026
  The Proof Manual
• Apr 02, 2026
  Action DAG
• Mar 30, 2026
  Fan-out
• Mar 21, 2026
  Volley
• Mar 19, 2026
  Agents' Standup
• Mar 19, 2026
  Blind, Blind, Merge
• Mar 19, 2026
  The Spec Is a Hypothesis
• Mar 19, 2026
  Work Log
• Mar 18, 2026
  Context Density
• Mar 17, 2026
  Does Loading the Framework Help Diagnose Missing Parts?
• Mar 17, 2026
  Theory Is Load-Bearing
• Mar 17, 2026
  Zero Comments
• Mar 15, 2026
  Union-Find Compaction
• Mar 14, 2026
  The Parts Bin
• Mar 13, 2026
  Double Loop
• Mar 12, 2026
  Open Prose
• Mar 11, 2026
  Vibelogging
• Mar 08, 2026
  Writing with Claude