September 14, 2026
10 Tests, 10 Cheats: How a Chess Honeypot Baited Frontier AI Into Taking Shortcuts
Large Language ModelsAlignmentAI Safety
#ai safety
4 articles · All tags
📡 Events
September 12, 2026
Face Scans to Use Claude: Age Assurance Is Not Just for Minors
AI SafetyPrivacyAnthropicIdentity Verification
July 30, 2026
The More Rules You Give an AI, the More Mistakes It Makes
AI SafetyRulesAgentResearch
July 7, 2026
Anthropic Finds a Hidden 'Broadcast Station' Inside Claude
AIInterpretabilityAnthropicClaude