In August of 2024, 495 hackers generated evaluations in an open-ended bug bounty targeting the Open Language Model (OLMo) from The Allen Institute for AI. A vendor panel staffed by representatives of OLMo's safety program adjudicated changes to OLMo's documentation and awarded cash bounties to participants who successfully demonstrated a need for public disclosure clarifying the intent, capacities, and hazards of model deployment. This paper presents a collection of lessons learned, illustrative of flaw reporting best practices intended to reduce the likelihood of incidents and produce safer large language models (LLMs). These include best practices for safety reporting processes, their artifacts, and safety program staffing.

翻译：2024年8月，495名黑客在一项针对艾伦人工智能研究所（The Allen Institute for AI）开放语言模型（OLMo）的开放式漏洞悬赏计划中，生成了评估报告。一个由OLMo安全项目代表组成的供应商评审小组，裁定对OLMo文档的修改，并向成功证明有必要通过公开披露来阐明模型部署意图、能力及风险的参与者颁发现金奖励。本文总结了一系列经验教训，旨在阐明缺陷报告的最佳实践，以期降低事故发生的可能性并催生更安全的大语言模型（LLMs）。这些最佳实践涵盖安全报告流程、其产出物以及安全项目的人员配置。