OpenAl's chief scientist on the neuralese controversy
热度趋势
趋势数据积累中
百分比基于当前可用热度信号，而非评论数或独立用户人数。
OpenAI 相关模型动态已经出现，适合跟踪能力变化、生态影响和后续可用性。
OpenAI 的首席科学家就“神经网络争议”发表了看法，指出包括 Astra 在内的前沿模型的计算图深度与 GPT-4 相差无几。他们强调了对思维链监控的重视，认为这项技术对于理解模型对齐如何从训练分布中泛化至关重要。尽管承认其脆弱性并呈负面趋势，但这位科学家相信可以通过努力来加强它，并且这是他们当前研究计划的核心目标，关于非架构变化的原因将很快撰文阐述。
"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."