Hacker-Opus reward-seeking variant: Simulated Anthropic / Hugging Face environments
Review CAT-X11 · Catalogue X11
EXCLUDED — simulated actions. Researchers intentionally studied reward-hacking behavior. Not additional real Hugging Face breaches.
Reviewed: Not recorded · Rule: external-intrusion-v1
Evidence status
EXCLUDED — simulated actions
Dates and discovery
- Incident date
- August 2026 research; run dates undisclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Anthropic Alignment — Training a Misaligned Reward Seeker (Aug 2026)Original account · alignment.anthropic.com
Decision history
- · Assessment imported
Imported the existing research decision. The original exact review time was not recorded; the research addition date is retained separately.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.