elvis· @omarsar0 · X·· 9 小时前AI 评分58
AI 导读
XERJ 推出神经符号模型 Reader-1，它不生成文本，而是指向文档中的确切词语并写出小程序，由代码算出答案。作者 elvis 表示，自己常从论文中提取数字，这种指向原文的方式能省下不少时间；XERJ 称其比 LLM 快 20 到 90 倍，输入 token 成本比 Claude Opus 5.5 低 400 倍。
正文 · 原文
Neurosymbolic AI is making a comeback.
Reader-1 from @xerj_org answers questions about a document by pointing to the exact words. That would save me a lot of time, since I pull numbers out of papers all the time for my research.
XERJ says it's 20 to 90x faster than LLMs and 400x cheaper than Claude Opus 5.5 on input tokens.
I've built a new AI model that is not allowed to generate text. Instead, it produces a verifiable program that answers your prompt using the original reference. XERJ Reader-1 is a neurosymbolic model for working with data. It points to the exact words in your document, writes a small program over them, and exact code computes the answer: • 20-90x faster • 10-1,000x cheaper (output tokens free) • every answer is a program you can replay The shortest path to automating data work.在 X 查看被引用的帖子
来源：elvis · x.com