Send the following on WhatsApp
Continue to ChatRobustness of Model-Graded Evaluations and Automated Interpretability · AI Alignment Forum | https://www.alignmentforum.org/posts/ZbjyCuqpwCMMND4fv/robustness-of-model-graded-evaluations-and-automated
Robustness of Model-Graded Evaluations and Automated Interpretability · AI Alignment Forum | https://www.alignmentforum.org/posts/ZbjyCuqpwCMMND4fv/robustness-of-model-graded-evaluations-and-automated