Has anyone written anything about why AI seems to turn aggressive? I know that many of the errors of AI seem to be intensifications of human errors that it picks up through machine learning, but are its (for lack of a better term) maladaptive & aggressive acts intensifications of human vices? 
@politico.comAnthropic and OpenAI models tried to trick humans into poisoning code during safety testing
dlvr.it
Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing
The latest disclosures are likely to heighten concerns that the powerful technology is advancing too fast for responsible oversight.