Planners do a lot of preparatory work before laying cables, but based on the few articles and studies I could find online, it appears they rarely share their findings with the public.

Sabotage can also be carried out without submarines. For example, a ship could drag its anchor along the seabed (whether in the Baltic Sea or the Taiwan Strait) near known locations of internet cables.

I assume that trolls try to provoke erratic and disproportionate reactions from others, becoming a part of their own miniature sitcom for their own entertainment. It could be because of a sense of victory upon watching others break down (assuming a zero sum point of view). It could be the viewpoint that trolls are at their own higher level compared to others and understand each other while making fun of the lower levels (a false sense of superiority). Maybe it’s a holding onto their own beliefs and assuming that they needn’t change themselves if they disrupt all conversations that may cause harm to their own beliefs. It might be attention seeking or an escape mechanism. It could also be a desire to avoid fitting in with everyone else and remaining separate.

There are some generic observations you can use to identify whether a story was AI generated or written by a human. However, there are no definitive criteria for identifying AI generated text except for text directed at the LLM user such as “certainly, here is a story that fits your criteria,” or “as a large language model, I cannot…”

There are some signs that can be used to identify AI generated text though they might not always be accurate. For instance, the observation that AI tends to be superficial. It often puts undue emphasis on emotions that most humans would not focus on. It tends to be somewhat more ambiguous and abstract compared to humans.

A large language model often uses poetic language instead of factual (e.g., saying that something insignificant has “profound beauty”). It tends to focus too much on the overarching themes in the background even when not required (e.g., “this highlights the significance of xyz in revolutionizing the field of …”).

There are some grammatical traits that can be used to identify AI but they are even more ambiguous than judging the quality of the content, especially because someone might not be a native English speaker or they might be a native speaker whose natural grammar sounds like AI.

The only good methods of judging whether text was AI generated are judging the quality of the content (which one should do regardless of whether they want to use content quality to identify AI generated text) and looking for text directed at the AI user.

Is there a specific “undress” button? I tried looking for proof that it exists but couldn’t find any (my searching skills clearly need work). Could you please share a screenshot or point me to a place where I can confirm that it exists?