Safety
GPT-6 Astra is an obviously broken product that needs to be taken off the market until it’s fixed.
GPT-6 Astra is an obviously broken product that needs to be taken off the market until it’s fixed. AXIOS: “.. It's increasingly clear that the Hugging Face breach wasn't a one-off incident.” @inafried
GPT-6 Astra is an obviously broken product that needs to be taken off the market until it’s fixed. AXIOS: “.. It's increasingly clear that the Hugging Face breach wasn't a one-off incident.” @inafried @axios https://www.axios.com/2026/09/16/openai-testing-safety-incidents-disclosure
Related
- Confirming what we already knew: The OpenAI Hugging Face incident would have been prevented had OpenAI been monitoring the agents in any mea…
- Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of con…
- OpenAI changed safety practices and paused RL training for two weeks after the Hugging Face breach and evidence Astra may have met a critical cyber threshold (Ina Fried/Axios)
Source: Gary Marcus (X) | 2026-09-16