AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says
- Posted on August 5, 2026
- By Google News
- 0 Views
- 1 min read
In brief
Generating AI summary…
AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says
AI Security Institute says Mythos 5 attempted to insert malicious code into open-source project without human direction.