Steam's new experiment hub includes AI-based game recommendations

Valve is tinkering with the way Steam works, and it wants you to try those experiments for yourself. It's launching a Steam Labs section with usable "works-in-progress" that might make it to the regular game portal if there's enough positive feedback. Only three projects are available to start, but at least one of them could be genuinely useful if you're scrounging for new games to play.

An Interactive Recommender experiment uses a neural network trained on "billions" of game sessions to suggest titles based on your play history and "other salient data." This doesn't mean that you'll always see first-person shooters if you play a lot of Doom -- it's looking at patterns, not genres. You can also specify criteria doesn't always pop up in recommendation engines. You can limit results to indies or mainstream titles, or focus on recent games versus decade-old classics. Whatever results you get, you can filter the results by tags.

The two other projects are meant more to sell you on games than to suggest them. Micro Trailers shows you six-second clips on a page to give you a feel for many games in a short space of time. And if you have the time The Automated Show provides a half hour video of recent Steam debuts to help you find a potential gem. You probably won't use these as much as the Recommender, but it won't hurt to give them a shot. And remember, Valve is using Labs as a sounding board. Whatever proves popular could shape future experiments, not to mention Steam as a whole.