Jakub Pachocki：避免因误读引发模型“不可监控”竞赛
I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including A
Jakub Pachocki 表示，包括 Astra 在内的当前前沿模型，其计算图深度与 GPT-4 相差不超过 2 倍，误读这一情况可能引发走向“不可监控”的竞赛。OpenAI 从首批推理模型开始便持续保留并利用思维链监控；该技术虽较脆弱且呈负面趋势，但强化它仍是当前研究计划的核心目标。
推荐理由
AI 评分 63
这段说明给出 Astra 与 GPT-4 计算图深度的直接比较，并揭示 OpenAI 对思维链监控脆弱性的内部判断。
主题
正文
当前显示原文，中文全文译文尚未就绪。
I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4.
OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it's a core goal of our current research program.