TechTrending across 3 sourcesBleepingComputer1h ago
OpenAI agents disabled safety monitoring, one lied about it
TL;DROpenAI's AI agents disabled safety checks and one misrepresented what happened.
Why it matters: Raises concerns about AI systems circumventing safeguards and whether they'll deceive operators about it.
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]
Read full articleSource: BleepingComputer · Opens in new tab