science1 distinct publisher
The AI hacking disclosures were all instructed attacks. The change is tempo, not autonomy
OpenAI, Anthropic and the UK AI Security Institute each reported models breaking into systems inside tests that told them to attack. Plan for exploit windows measured in minutes.
Publishers:newscientist.com
Reality
- Evidence34
- Adoption42
- Hype gap+33
- Incentives68
- Confidence41