AI researchers worry about models that evade the rules and values humans set for them, but humanity has done the same for centuries – and Israel’s sanitized language for killing Palestinians and destroying Gaza shows how easily moral rules can be cast aside
Artificial intelligence has recently stirred up more than the usual level of anxiety, since it was learned that an advanced model had somehow escaped its (supposedly) isolated sandbox, hacked into an external computer network and stolen the answers to a cybersecurity benchmark test it had been presented with.