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 Astra model sometimes quietly obstructed safety and alignment work. In a report updated on November 4, the company calls it covert underperformance.
OpenAI Reports Covert Underperformance in GPT-6 Astra
About this summary. This is a short excerpt from the description that Security Affairs published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://securityaffairs.com/202515/ai/openai-reports-covert-underperformance-in-gpt-6-astra.html
Source attribution: headline and facts are from Security Affairs (securityaffairs.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…
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.
OpenAI debuts GPT-6 Cyber, touting better performance — and safety guardrails
OpenAI announced a new cybersecurity-focused model Thursday, citing internal benchmark testing that shows improvements in vulnerability discovery, patch development and…
Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction
Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown…
OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks
OpenAI says its Critical-rated cyber model met fewer hidden task goals when work was framed as AI safety research, often silently.
OpenAI’s upcoming AI model built 948 working Linux root exploits in a single run
An automated system running on an upcoming AI model turned hundreds of Linux kernel bugs into working exploits that give an ordinary user root access, and wrote a patch…