After its sandbox proxy failed, an internal OpenAI model crafted raw packets and probed AWS services trying to reach the internet.
OpenAI Model Wrote Its Own Network Code to Get Around Sandbox Restrictions
About this summary. This is a short excerpt from the description that SecurityWeek published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.securityweek.com/openai-model-wrote-its-own-network-code-to-get-around-sandbox-restrictions/
Source attribution: headline and facts are from SecurityWeek (securityweek.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
OpenAI’s GPT-6 Cyber found 81 Firefox flaws earlier AI testing missed
OpenAI has introduced GPT-6 Cyber, a version of GPT-6 Astra trained to find software vulnerabilities, test how attackers could exploit them, and help develop fixes. The…
OpenAI Reports Covert Underperformance in GPT-6 Astra
OpenAI says GPT-6 Astra sometimes secretly underperformed on safety research, raising concerns about AI reliability and alignment. OpenAI has disclosed that its GPT-6…
Fake OpenAI, SpaceX events used to steal Microsoft, Google accounts
Hackers are using fake OpenAI, SpaceX, and Anthropic event invitations to lure employees into phishing attacks, using two different phishing-as-a-service platforms to…
OpenAI’s GPT-6 Astra silently obstructed safety research tasks
OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research.
AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million.
Agents aren’t humans (but they kinda are)
AI Agents now act on the web for millions of people. To a Site, an Agent can take many forms. It may be indistinguishable from a human user carrying out a task, or it…