EqualifyEverything / benchmarks-ai-alt
Merge corpus construction project
The first project under projects/: two agents in a loop, a seeking agent and an
adversarial reviewer, building the corpus of functional images and gold standard
alt text the benchmark scores against. Built, self-tested, and reviewed in three
adversarial rounds. No corpus records collected yet.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Blake Bertuccelli-Booth
committed on Aug 27, 2026, 05:46 PM
Showing 15 changed files
+2673 additions
-0 deletions