Nice website and a good exercise! We really are living in a golden age when we can identify most LLM written stuff. Longer from posts are currently easier to identify than shorter. (I ended early got 4/5 The long dashes and general questions to the audience not the commenter were a tell)

Very soon we won't be able to tell any difference or identify any signs.

Some (but not all) of the AI comments are prefixed by an extra blank line. I got S (5/5), A (4/5), and A (4/5) using this tell. Took me less than a minute on the first one (as it took a few seconds to notice the blank line), the second one took 18s, and the third one took 22s.

psychosis.hn is a daily game. Every day we fetch three stories from a previous front page of HN, each with 5-7 AI comments threaded into the discussion. They have personas, reply to real people, and sometimes have real comments reparented underneath them.

First try I got 0/5 with 3 false positives, by the third i got 4/5 with 1 false positive.

it's getting scary, i don't know how much longer we can tell humans apart from AI