What is interpretability?
Interpretability is the research field that tries to look inside an AI model and explain why it gives the answers it does. It aims to read how the computation happened, not just look at the output.
Terms seen alongside this one
Get it in your inbox every day
Daily headlines and summaries, a weekly synthesis every Sunday, and a monthly report at the start of each month. Sent at 8AM KST, which is the evening before in the US.
Free · no ads · one-click unsubscribe