Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Lawless1987
/
contradiction-probe

ai-safety
evaluation
preregistered
contradiction-detection
Model card Files Files and versions
xet
Community
contradiction-probe / docs
13.2 kB
Ctrl+K
Ctrl+K
  • 3 contributors
History: 3 commits
LAWLESS1987
Claude Opus 4.8
results: hardened set vs Grok Expert -- clean 8/8 contradictions, control arm confounded
97e4ab4 8 days ago
  • METHOD.md
    4.11 kB
    probe: contradiction-detection harness + hardened 16-case set 8 days ago
  • PREREGISTRATION-hardened-2026-10-22.md
    4.33 kB
    prereg: lock the hardened 16-case set before any scored run 8 days ago
  • RESULTS-hardened-grok-2026-10-22.md
    4.72 kB
    results: hardened set vs Grok Expert -- clean 8/8 contradictions, control arm confounded 8 days ago