Hamel Husain

@hamelhusain

Q: How can I do AI evals when traces contain sensitive data? A: Four approaches: negotiate access to a defined scope, work with authorized experts, redaction and synthetic data. https://hamel.dev/blog/posts/evals-faq/how-can-i-do-error-analysis-when-production-traces-contain-sensitive-data.html
打开原帖#511482
  1. Frontier

    Microsoft introduces Quine for biology
  2. Frontier

    Kumo predicts table labels in one pass
  3. Frontier

    Astra's simulated attack rate hit 29.2%