In a recent blog post titled “We Need a Science of Evals” the AI alignment-focused research organisation Apollo Research advocates for the establishment of a "Science of Evals". While we applaud the initiative, and precisely because we stand behind the overall message, we have some comments to add on culture, history, and reinventing the wheel.
Share this post
2024 February "AI Evaluation" Digest
Share this post
In a recent blog post titled “We Need a Science of Evals” the AI alignment-focused research organisation Apollo Research advocates for the establishment of a "Science of Evals". While we applaud the initiative, and precisely because we stand behind the overall message, we have some comments to add on culture, history, and reinventing the wheel.