Re:Building an AI game studio: what we've learned so far
by jprete on Tuesday May 21, 2024 @04:10PM
(#40433261)
If the AI doesn't get the mechanics right, and you have subtle game-breaking bugs that make it impossible to complete, you will never be able to fix it.
[ Parent
| on HN ]
Re:Building an AI game studio: what we've learned so far
by antifa on Tuesday May 21, 2024 @04:55PM
(#40433794)
> you will never be able to fix it.
I don't know about the article's studio specifically, but regarding AI game engines, I'm mostly worried you won't be able to make engine edits, or the engine will only be able to make an extremely narrow subset of games, or exiting the WYSIWYG/SaaS means starting over from scratch. If the engine targets a specific genre, it could cause a flood of low effort garbage. Some genres are already flooded because the easier game engines have tutorials and asset packs for them.
Re:Building an AI game studio: what we've learned so far
by fabiopolimeni on Tuesday May 21, 2024 @04:33PM
(#40433519)
AI can create bugs, sure, as well as humans do. With time, I am more inclined to think it will be easier to ask an AI to fix them for us rather than the other way around.
There is a non-intuitive feature of current LLMs, and that is, they are capable of refining over and over their own previous outcome. You can ask to revisit it, to improve it, check it, etc etc. use this to fix its own bugs.