Termsslug: model-forensics

Model Forensics

模型取证

Safety evaluation method that inspects internal computation to detect known risks and anomalies during training.

Curated Intelligence

1 items · Page 1/1
IT之家 · IT业界T2·Industry
78 pts
OpenAI Partners with Goodfire on Embedded Model Interpretability Audits

OpenAI launched its first Embedded Assessments program with Goodfire, Apollo Research, METR and Transluce, granting outside experts deep access to internal models, checkpoints and training data. Goodfire will embed interpretability researchers to perform model forensics on training-time anomalies. OpenAI had earlier explored acquiring Goodfire for over $5 billion, but the startup chose to stay independent and sell to multiple labs.