Anthropic says AI could one day ‘sabotage’ humanity but it’s fine for now
The firm investigated four distinct “sabotage” threat vectors for AI and determined that “minimal mitigations” were sufficient for current models.
Artificial intelligence firm Anthropic recently published new research identifying a set of potential “sabotage” threats to humanity posed by advanced AI models.
According to the company, the research focused on four specific ways a malicious AI model could trick a human into making a dangerous or harmful decision.
Source: Anthropic
Go to Source
Author: Tristan Greene
