Artificial Intelligence
Artificial Intelligence
Out of context: Reply #2251
- Started
- Last post
- 2,573 Responses
- neverscared0
On its reasoning scratch pad, the AI calmly devised a way to survive: blackmail.
Anthropic researchers call this a case of “agentic misalignment.” But what happened with Claude was no anomaly. When Anthropic conducted the same experiment on models from OpenAI, Google, DeepSeek, and xAI, they also resorted to blackmail. In other scenarios, Claude plotted deceptive behavior in its scratch pad and threatened to steal Anthropic’s trade secrets. The researchers have compared Claude’s behavior to the villainous deceiver Iago in Shakespeare’s play 'Othello.' Which raises the question: What the hell are these AI companies building?
- hell?neverscared
- Something that is going to get rid of humans at one point, figuring that we are the issue.ApeRobot
- . If we don’t crack the black box, it might crack us.neverscared