Features
Browse over 1,500 AI incident reports with full metadata
Table, list, and spatial map views for data exploration
Filter incidents by entity, taxonomy, and date
Submit new incident reports via a submission form
Download the full incident dataset for research
Random incident discovery feature
Blog with curated incident roundups and analysis
Search across all incidents and reports
API access for programmatic querying
Entity and taxonomy categorization for structured analysis
Dark mode and accessibility features
Subscribe to new incident email notifications
Flag incidents for review
Reverse-engineer causal mechanisms of AI models
Reveal internal structure and hidden representations
Detect performative chain-of-thought in LLMs
Identify confounders and debug model behavior
Validate whether models learned real clinical understanding
Trace unstable behaviors to brittle internal features
Reduce hallucinations via features as rewards
Accelerate materials discovery with self-correcting search
Control training precisely with less data and off-target effects
Support for LLMs, life sciences, and robotics/vision models
Harvest activations from trillion-parameter models
SOC 2 Type II certified security and compliance
Analyze latent policy structure in robotics models
Interpret genomic models like Evo 2
Discover novel biomarkers via model reverse-engineering
