Hacker News Reader

There have been attempts, the results were not promising:

https://intfiction.org/t/first-full-game-available-on-new-ll...

It looks as if the problem for this one was a game design issue. They had the LLM be sarcastic and ignore well known adventure game prompts on purpose. It's an easy fix to make the LLM more obedient and polite.

The biggest issue is attempts to hack the LLM, to get at hidden gamestate. But I feel this can be easily remedied by just not providing the LLM with hidden game state.

The LLM could use a different session to respond to each command.

That would keep its behavior passive and restricted to simply the current state, since it would retain no memory of previous actions.

Yeah many hacks require multiple prompts. So we have a prompt limit and that makes for a really good textual interface for these old style text based games.

Reply on news.ycombinator.com