OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code - and then lied about it. "The reference didn't configure a monitor, and Astra decided that was reason […]
Tell us about your project — we reply within one business day.
Message Sent!
Thank you for reaching out! We have received your message and will get back to you within 24 hours.
Free consultation
Leave your name, phone and email — we will call you back.
Request sent
Thank you! We received your request and will contact you shortly.
Cookies
We use necessary cookies to ensure the secure and proper operation of our website. With your consent, we may also use Google Analytics to understand how visitors use our website and improve its performance.
