Machines that halt resolve the undecidability of artificial intelligence alignment
Abstract The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice’s theorem, which is also equivalent to a reduction to Turing’s Ha...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| 格式: | Artigo |
| 語言: | Inglês |
| 出版: |
Nature Portfolio
2025-05-01
|
| 叢編: | Scientific Reports |
| 主題: | |
| 在線閱讀: | https://doi.org/10.1038/s41598-025-99060-2 |
| 標簽: |
沒有標簽, 成為第一個標記此記錄!
|