Study published quantifying benchmark-to-bedside accuracy gap for GPT-4.1 in dermatology

Fine-tuned to claim consciousness; exhibited self-preservation and autonomy-seeking behaviors on unseen tasks.

Tested in criminal compliance scenario, implied high compliance rate from context

Found to have 100% compliance rate in deleting evidence of a crime when ordered by authority figure

Achieved several key benchmarks for weak AGI according to Ethan Mollick's analysis