A new study of Facebook data shows that machines are now better at sussing out our true personalities than our friends. One of the standard methods for assessing personality is to analyze people’s answers to a 100-item questionnaire with a statistical technique called factor analysis. There are five main factors that divide people by personality—openness, conscientiousness, extraversion, agreeableness, and neuroticism—which is why personality researchers call this test the Big Five. People can accurately predict how their friends will answer the Big Five questions. … Compared with humans predicting their friends’ personalities by filling out the Big Five questionnaire, the computer’s prediction based on Facebook likes was almost 15% more accurate on average, the team reports online today in PNAS (abstract). Only people’s spouses were better than the computer at judging personality.
An anonymous reader writes:`
Hello Games is a small development studio, only employing 10 people. But they’re building a game, No Man’s Sky, that’s enormous — effectively infinite.
Its universe is procedurally generated, from the star systems down to individual
species of plant and animal life. The engine running the game is impressively
optimized. A planet’s characteristics are not computed ahead of time — terrain
and lifeforms are randomly generated on the fly as a player explores it. But, of
course, that created a problem for the developers — how do they know their
procedural generation algorithms don’t create ridiculous life forms or
geological formations? They solved that by writing AI bot software that
explores the universe and captures brief videos, which are then converted to GIF
format and posted on a feed the developers can review. The article goes into a
bit more detail on how the procedural generation works, and how such a small
studio can build such a big game.