[–] 6 points 1 year ago (3 children)

It’s such a liminal game. Love it. Some colossi are frustrating, though, but remember they all have a strategy to them — the battles are like puzzles. Don’t be ashamed to look up the solutions if you get stuck. They still take some skill to carry out once you’ve figured them out.

  • source
  • [–] 1 point 1 year ago (1 child)

    Those are, FWIW, relatively poor LLMs. Don’t get me wrong, I absolutely don’t support the idea of LLMs standing in for human emotional support, but had they run the experiment on Copilot or ChatGPT I’d wager they’d get different results. The way those two seemingly pick up on nuances and subtext is scary for a machine. That being said, they’ve shown more enabling and sycophant behaviour recently, so idk.

  • source