AI Safety Research, Explained for Absolute Beginners
A jargon-free tour of AI safety research — alignment, misuse, oversight, and the handful of papers a total beginner should actually read first.
#interpretability
1 article with this tag.
1 article with this tag.
A jargon-free tour of AI safety research — alignment, misuse, oversight, and the handful of papers a total beginner should actually read first.