Diet and exercise are often referred to as lifestyle "choices". And many people seem to be making poor choices. Can recommender systems help? Maybe. But we should be careful not to apply them where they can't help. I will suggest that they are potentially useful for problems of discovery and attention focusing, but not for in-depth evaluation and especially not for motivation, where the desirable action is known but not taken. I will offer examples of both promising and not-so-promising opportunities for exploration of recommender system applications in health behavior change, and suggest other conceptual frameworks that may be more useful where recommender systems are not the right lens. Professor Resnick's research focuses on SocioTechnical Capital, productive social relations that are enabled by the ongoing use of information and communication technology. His current projects include making recommender systems resistant to manipulation through rater reputations, nudging people toward politically balanced news consumption and health behavior change, and crowdsourcing fact-correction on the Internet. Resnick was a pioneer in the field of recommender systems (sometimes called collaborative filtering or social filtering). Recommender systems guide people to interesting materials based on recommendations from other people. The GroupLens system he helped develop was awarded the 2010 ACM Software Systems Award. His articles have appeared in Scientific American, Wired, Communications of the ACM, The American Economic Review, Management Science, and many other venues. He has a forthcoming MIT Press book (coauthored with Robert Kraut), titled “Building Successful Online Communities: Evidencebased Social Design”.