Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Claude Uses iWSP to Program Interpretable Transformer Weights

AI summary

Microsoft Research and three universities introduced Interpretable Weight Space Programming (iWSP), which uses Claude-generated Python code and validation feedback to set Transformer weights without gradient-based training. The report says networks created across 13 algorithmic task classes reached 100% hidden-test accuracy in 26 runs, while applications to brain-data modeling produced interpretable features and exposed a confound. Performance was weaker on natural-language tasks, where models grew to roughly 190,000 parameters and sentiment classification reached 72%.

In-depth insight

The study offers a new route to inspectable neural-network construction, but its strong algorithmic results do not establish that gradient-based training is unnecessary for complex language tasks or foundation models.

在13类复杂的算法任务、26次独立运行中,一个全新的神经网络在隐藏测试集上全部达到了100%的准确率。

更不可思议的是,整个过程没有喂给它海量数据,甚至完全没有使用「反向传播」和「梯度下降」。

这个晶莹剔透、小巧至极的满分神经网络,是Claude Opus 5.5,用代码一行一行直接「手写」出来的。

近日,微软研究院联合约翰斯·霍普金斯大学、哥伦比亚大学和纽约大学的团队,发表了新研究「可解释权重空间编程(iWSP)」。

这项研究证明:前沿大语言模型已经可以直接越过传统的优化器,依据固定的评测反馈,像外科医生一样精准构思计算逻辑,并用代码将算法直接写进Transformer的权重里。

#Microsoft Research#Johns Hopkins University#Columbia University#New York University#Anthropic#Claude Opus 5.5#Claude Opus 4.7#Claude Sonnet 5.5#Claude Haiku 5.5

Original · 7 min readRead the original
Group chat

No comments yet. Start the conversation.