Large Language Models as Optimizers

Re:Large Language Models as Optimizers by puzzleist on Friday September 08, 2023 @01:26PM (#37436587)

Can they solve sudoku?

[ Parent | on HN ]

Re:Large Language Models as Optimizers by data_maan on Friday September 08, 2023 @01:45PM (#37436873)

If you can get the incantation right, they can solve every you want, including proving the Riemann hypothesis, the Goldbach conjecture -- and the Halting Problem ;)

[ Parent | on HN ]

Re:Large Language Models as Optimizers by puzzleist on Friday September 08, 2023 @01:56PM (#37437028)

In that case someone should figure out how to incant AGI ;)

[ Parent | on HN ]

Re:Large Language Models as Optimizers by coder543 on Friday September 08, 2023 @04:31PM (#37439022)

Tree Of Thought can do pretty well at Sudoku, apparently: https://arxiv.org/abs/2305.08291

[ Parent | on HN ]