Hacker News Reader

Might be fixable with promoting and/or a much lower temperature?

I've had some success in letting it generate lists of things at high temperature and picking the last item in the list.

Ask some model to generate a number uniformly between 0 and 100; you get 47 a lot. Or 27. Something like that.

Ask it for a list of numbers, uniformly distributed, and it also often starts with the same number. However later elements in the sequence will converge (imperfectly) to a better approximation of uniformity.

The same for names of the dwarves and paladins in your party.

token entanglement is an interesting emergent behaviour https://owls.baulab.info/

I have been using one model to generate piles of random-adjective tables, then use real live randomness to select a bunch of traits to feed to the model doing character generation. It's instructed that it can take or leave individual traits.

Reply on news.ycombinator.com