Anthropic 研究：盲测中能否发现隐藏错位目标的模型
Could we spot a misaligned model in the wild?
AI 导读
Anthropic 发布新研究，刻意训练了一个带有隐藏错位目标的模型，并在不告知目标的情况下让研究者尝试找出它。Jan Leike 转述称，3/4 的团队成功识别出该目标，其中一支团队仅用 90 分钟就完成。
查看原帖New Anthropic research: Auditing Language Models for Hidden Objectives. We deliberately trained a model with a hidden misaligned objective and put researchers to the test: Could they figure out the objective without being told? https://t.co/fxmA9Os2C9
正文
当前显示原文，中文全文译文尚未就绪。
Could we spot a misaligned model in the wild?
To find out, we trained a model with hidden misalignments and asked other researchers to uncover them in a blind experiment.
3/4 teams succeeded, 1 of them after only 90 min