A Proposal for Safe and Hallucination-free Coding AI
- 출판
Preface
In this essay, I propose a research agenda that I believe will eventually lead to coding AIs that have superhuman-level ability, are hallucination-free, and safe. To achieve our goal will require a lot of further innovation, experimentation, and hard work. But I fully believe this is the most promising direction. (…omitted…)
gasstationmanager.github.io/ai/2024/11/04/a-proposal.html