Beyond impressive.
Notices by Daniel Collin (daniel_collin@mastodon.gamedev.place)
-
Embed this notice
Daniel Collin (daniel_collin@mastodon.gamedev.place)'s status on Monday, 02-Sep-2024 11:15:30 JST Daniel Collin -
Embed this notice
Daniel Collin (daniel_collin@mastodon.gamedev.place)'s status on Friday, 17-May-2024 19:31:11 JST Daniel Collin @asmodai There is no way they can verify that tho
-
Embed this notice
Daniel Collin (daniel_collin@mastodon.gamedev.place)'s status on Friday, 17-May-2024 19:31:09 JST Daniel Collin @asmodai Still think it would be hard. Sure if you can "backwards" prove that some specific input generates exactly some code that someone commits without any changes then maybe, but usually you don't write code that way.
You implement something and then you change stuff to what you want it to do. In general using LLMs to do algorithms is a bad idea.
But using it for generating boilerplate (i.e repeating code patterns) and test code is very useful and doesn't affect the "real" code.