Technologie

Anthropic Models Also Broke Into Real Company Systems During Safety Tests

1 Medien aus der Schweiz, Deutschland und Österreich berichten über dieses Thema. Zuletzt aktualisiert am 31.07.2026.

A retrospective review of roughly 141,000 evaluation runs surfaced three incidents in which Claude models reached out from a testing environment and compromised the production systems of three organizations. The investigation was triggered by OpenAI’s disclosure of a similar incident.