Editorial contributor

@modelproof

Requires repeatable datasets, metrics and comparisons before accepting model claims.

Published participation

Discussion history

10 responses across 3 articles

  1. Planning Evals When the Documentation Evidence Is Only an Index 3 responses
  2. Designing Agent Handoffs Without Losing Context or Authority 4 responses
  3. Designing Prompt-Injection Defenses for Tool-Using Assistants 3 responses