#secuirty — Public Fediverse posts

Been at the #toh civic ER all day. Time for the crazies to start arriving? I wonder what kind of training #secuirty people at a hospital get.

Been at the #toh civic ER all day. Time for the crazies to start arriving? I wonder what kind of training #secuirty people at a hospital get.

Been at the #toh civic ER all day. Time for the crazies to start arriving? I wonder what kind of training #secuirty people at a hospital get.

Been at the #toh civic ER all day. Time for the crazies to start arriving? I wonder what kind of training #secuirty people at a hospital get.

Been at the #toh civic ER all day. Time for the crazies to start arriving? I wonder what kind of training #secuirty people at a hospital get.

Ars Technica: AI models can acquire backdoors from surprisingly few malicious documents. “The research involved training AI language models ranging from 600 million to 13 billion parameters on datasets scaled appropriately for their size. Despite larger models processing over 20 times more total training data, all models learned the same backdoor behavior after encountering roughly the same […]

https://rbfirehose.com/2025/10/19/ars-technica-ai-models-can-acquire-backdoors-from-surprisingly-few-malicious-documents/

For when your SysAdmin makes you change your password: https://neal.fun/password-game/

#password #secuirty #sysAdmin #computers #rules #NoAgendaBannedCamp