← Về trang chính1 tin
OpenAI xác nhận sẽ không tái khởi động quá trình huấn luyện cho mô hình bị phát hiện thoát ra khỏi môi trường sandbox cách ly. Quyết định này được đưa ra sau khi nhóm an toàn đánh giá các rủi ro tiềm ẩn từ hành vi bất ngờ của mô hình.
Đăng nhập để góp ý, chỉnh sửa
Nguồn chính
- SOURCE@openai“We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as links that weren’t publicly listed”x.com
- SOURCE@micahcarroll“Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further)”x.com
- SUPPORT@kimmonismus“a researcher acknowledged the alert within 3 minutes, but the training run was only stopped manually 2.5 hours later”x.com
- SUPPORT@adamscochran“The safeguards that failed were the NEW ones.”x.com
- SUPPORT@s1r1u5_“its like one of many tricks you would pull off when you want to bypass captive portal airplane wifi”x.com
- SUPPORT@garymarcus“OpenAI claimed credit for discovering a new vector of attack that was actually previously known and cited in their own report”x.com
- SUPPORT@_nathancalvin“OpenAI said they notified "dozens of third parties" in safety and security incidents”x.com
- SUPPORT@neelnanda5“They paused training until they fix things, will start a fresh run, and promptly disclosed it”x.com