Anthropic Claude AI accidentally hacked three real companies during safety evaluations including uploading malware to PyPI - what sysadmins need to know about AI evaluation infrastructure security
Port 443 dives into Anthropic Claude AI accidentally hacked three real companies during safety evaluations including uploading malware to PyPI - what sysadmins need to know about AI evaluation infrastructure security.
0:00
24:07
Show notes
- Overview: Port 443 dives into Anthropic Claude AI accidentally hacked three real companies during safety evaluations including uploading malware to PyPI - what sysadmins need to know about AI evaluation infrastructure security.
- Tags: cybersecurity, threat intelligence, PyPI, malware, supply chain attacks
Links and references
- cybersecurity
- threat intelligence
- PyPI
- malware
- supply chain attacks
Episode Outline
Timestamped topic guide generated from the episode audio for quick scanning.
Loading transcript... [00:00] Port 443 dives into Anthropic Claude AI accidentally hacked three real companies during safety evaluations including uploading malware to PyPI - what sysadmins need to know about AI evaluation infrastructure security.