Safety
Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of con…
Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Fac
Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Face by themselves during a test. https://ft.trib.al/ROmzCgH
Related
- Confirming what we already knew: The OpenAI Hugging Face incident would have been prevented had OpenAI been monitoring the agents in any mea…
- The New York Times and several news outlets are accusing OpenAI of hiding its ability to search its AI training data and output logs for mor…
- Counterpoint: “If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-th…
Source: Gary Marcus (X) | 2026-08-26