Hacker News Reader

This is kinda like that thing about how psychic mediums supposedly can't medium if there's a skeptic in the room. Goes to show that AI really is a modern-day ouija board.

View on HN

The accurate inferences that can be drawn from subtle linguistic attributes should freak you out more than they do.

Switching one good synonym can send the model off an entirely different direction in response, or so I’ve observed.

If I could give an LLM to any historical figure, I would give it to Nietzsche.

Reply on news.ycombinator.com