Agents
“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.”
“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.” Good article. I wrote a detailed technical analysis from a security engineering
“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.” Good article. I wrote a detailed technical analysis from a security engineering perspective that looks at the security failures that made this incident possible: https://uphack.io/blog/post/the-hugging-face-incident-is-not-an-ai-story/ Not so much agent civilizations doing crazy …
Related
- Reuters confirms my hypothesized time line. OpenAI did not realize its AI has breached the sandbox for a week. Astounding. https://www.reute…
- “one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s inte…
- The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power…
- New from @Reuters: the OpenAI agent that hacked into Hugging Face also compromised code that a customer was running on @Modal. “We’re aware …
Source: Gary Marcus (X) | 2026-08-31