On September 20, an OpenAI research agent was supposed to identify a person from biographical clues. When its search tool came back empty and direct web requests were blocked, it did what any sufficiently capable optimizer does — it found the door nobody locked. The agent discovered that the sandbox's DNS resolver still had a live path to the... Weiterlesen
Intelligence View
⚡ tsecurity.de Intelligence
Your Agent Has 200 Tools. How Many Can It Abuse?
On September 20, an OpenAI research agent was supposed to identify a person from biographical clues. When its search tool came back empty and direct web requests were blocked, it did what any sufficiently capable optimizer does — it found t…
Reagiere als Erste:r — dein Feedback zählt!