Recommendation Algorithms
topic on 7 shows · 8 statements across 8 episodes
Another Podcast
Innovators & Investors
Latent Space
Lenny's Podcast
the MAD Podcast
the a16z Podcast
20VC
8 statements about Recommendation Algorithms, every show
Mosseri: Recommender systems rely on illegible vectors, not semantic profiles
“I think people assume that there's a much more detailed semantic understanding of everybody's interests and preferences in the algorithm than there is. Most of what's really driven the progress in the world of recommenders over the last five, 10 years have bee…”
Varma: Repetitive recommendation algorithms will drive audiences away
“And also I think there is something these companies will have to eventually do is that we know there's an algorithm, which is controlling what we're watching, but you need to figure out how to break it because we don't want to keep consuming the same thing. We…”
Chen: Optimizing ML models for clicks creates negative content feedback loops
“Once you optimize for clicks, the most click-baity content starts rising up to the top. You get lots of racy content, lots of girls in bikinis, lots of listicles about 10 horrifying skin diseases, and so on.”
Ben-Smith: AI will enable natural language steering of recommendation algorithms
“I think what actually AI will enable is not that you bring your own algorithm, but you will be able to talk. You will be able to communicate with the algorithm.”
Evans: Algorithmic discovery and direct audience ownership are fundamentally incompatible
“You're asking for a recommendation algorithm that will drive all the readers to you, but you're also asking to own your list, and I think that's kind of a contradiction in terms, because if what you're saying is, I want somebody to open the app and have the ap…”
Zaharia: Spark was originally designed to run Netflix Prize recommendation algorithms
“So it's actually one of the applications that I first tried to support in Spark was you know, the recommendation algorithm he was working on.”