Imagine it's Sunday. You're planning a BBQ for a week from today, but the weather person on TV just forecast rain for next Sunday. How much confidence do you really have in that prediction? Turns out, that's about the confidence we can place in predicting coral bleaching from SST alone. Our new paper in PeerJ dives into these statistics and proposes some initial steps forward. The main conclusion is that we should critically evaluate our understanding of the causes of bleaching events, think beyond SST, and work together to improve our predictive ability.