Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
2 results for “evaluation metrics”
SPIN Processed News Frame: The Fog
OpenAI quietly boosts some of Astra's evaluation metrics, and continues to change others post-launch - fortune.com
OpenAI adjusted evaluation metrics for its Astra AI system after launch, including boosting some scores and continuing to modify others, without public explanation or transparency about the rationale, methodology, or impact of those changes.
Spin 85% Needs Evidence AI Risk Moderate
Fortune AI / Business via Google News
Sep 5, 2026
SPIN Processed News Frame: The Cushion
Evaluating RAG Metrics in Applied Contexts: An Experiment, Its Findings and Its Limitations
A research paper evaluates how well automated RAG evaluation metrics align with human judgment using a business-domain QA dataset, finding mixed correlations and noting methodological limitations.
Spin 25% Claim Present in Source AI Risk Moderate
arXiv Computation and Language
Jul 10, 2026