公开(公告)号：US20250165589A1

公开(公告)日：2025-05-22

申请号：US18518257

申请日：2023-11-22

Applicant: Amazon Technologies, Inc.

Inventor： Vinayshekhar BANNIHATTI KUMAR ,  Sopan KHOSLA ,  Hayden LAWLER ,  Siddharth Satish GOYAL ,  Rashmi GANGADHARAIAH ,  Brijesh LUCKRIA ,  James W. HORSLEY ,  Bhaskar Hosahalli RANGASWAMY ,  Abhijit S. BARDE

IPC: G06F21/55

Abstract: Techniques for filtering for harmful generative artificial intelligence (AI) results are described. An example of filtering includes receiving a request for an input phrase to be responded to by a generative AI model; comparing to the received input phrase to at least one known harmful input phrase to determine that the received input phrase is to be provided to the generative AI model; providing the received input phrase to the generative AI model; and generating a response by at least in part on an output of the generative AI model.