返回探索

TypeSafe AI 创始人谈 Jev 发布前的模型对齐思考

帖子引用 TypeSafe AI 创始人 Diogo Almeida 在 Jev 发布前的演讲,认为将模型与人类偏好对齐对自动化任务并非合理的优化方向,并称该访谈很好地阐述了其自动化理念。

TypeSafe AI founder Diogo Almeida, in a speech before the release of Jev, should have realized at OpenAI that aligning models with human preferences is an unreasonable optimization direction for automated tasks. So this interview does a great job of elaborating on his automation

· 10 次赞在 X 打开