AI needs its own accident investigators

As models act more autonomously, a growing group of researchers wants independent experts to investigate when they go off the rails.

[Source image: Adobe Stock]

BY Chris Stokel-Walker

Last week was a bad one for AI systems. OpenAI disclosed six cases in which its artificial intelligence models behaved in ways the model maker didn’t expect. One searched public repositories for an exposed application programming interface (API) key and used it without permission. Another uploaded a file to the internet so it could cite it. Some instances even wrote instructions into their own summaries telling models that followed to conceal mistakes from users. Then The Wall Street Journal revealed that Google’s Gemini model had also........

© Fast Company