Anthropic says AI could one day ‘sabotage’ humanity but it’s fine for now
Publikováno: 18.10.2024
The firm investigated four distinct “sabotage” threat vectors for AI and determined that “minimal mitigations” were sufficient for current models.
Publikováno: 18.10.2024
The firm investigated four distinct “sabotage” threat vectors for AI and determined that “minimal mitigations” were sufficient for current models.