THE COLLECTION
EVERY SIGNAL, SORTED.
Search the whole shelf by topic, tool, term, or plain old curiosity.
SHOWING 1 OF 521 STORIES
ISSUE 569MORNING
United States, OpenAI, Evals, Promptfoo, Evaluation Migration, AI Quality, Regression Testing, Datasets, Graders, Human Review, Reproducibility, Audit Evidence, Model Governance and Developer Tools
OpenAI made its Evals platform read only. Export the evidence before shutdown
OpenAI has frozen existing Evals and scheduled the dashboard and API to shut down on November 30. The migration job is not copying a score. It is preserving enough evidence to rerun the test, explain the result and notice when the replacement behaves differently.