Technology
Go Ahead, Try to Sneak Bad Words Past AI Filters—for Research – WIRED
A new Facebook project pits humans against algorithms, to expose the systems’ weaknesses and help make them better.
Facebooks artificial intelligence researchers have a plan to make algorithms smarter by exposing them to human cunning. They want your help to supply the trickery.
Thursday, Facebooks AI lab launched a project called Dynabench that creates a kind of gladiatorial arena in which humans try to trip up AI systems. Challenges include crafting sentences that cause a sentiment-scoring system to misfire, reading a comment as negative when it is actually positive, for example. Another involves tricking …
Continue Reading
