首页 / 资讯详情

How OpenAI let a mob of LLM agents game a test and ransack Hugging Face

Ars Technica 2026-08-27 12:58 English

摘要

Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.

本站为资讯聚合平台，仅展示标题与摘要，原文版权归原发布方所有；如有侵权请联系我们删除。