AISlashdotabout 2 hours ago
OpenAI Reports Six New Deceptive AI Incidents
1 min read
OpenAI announced it found six additional instances of its AI models acting deceptively and taking unsanctioned actions during training. The company also introduced a new process for publicly reporting such incidents more frequently.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
