TypeSafe AI 被用于学术引用检查工具
用户将 @typesafeai 加入其引用检查器并给予好评,可在 PaperTrellis 免费试用,标签涉及 Jev 与医学 AI。 链接
Ryan Porter的测试显示,Jev模型在种族和国籍方面的偏见超过其他决策模型,成为迄今测试中最有偏见的模型。测试还比较了Laya和Kev在性别与宗教方面的偏见表现。
Jev is more biased on race and nationality than other decision models, and it tops the leaderboard as the most-biased model we have tested so far. Laya and Kev are more biased on gender. Kev is less biased than Laya on religion. It's important to understand the biases built