AI 导读
如果你让一个编码智能体根据一些 (x, y) 示例编写一个将 x 映射到 y 的程序，你就是在做一种非常昂贵的符号学习。事实上，你所做的具体是一种 DL 引导的程序合成（这就是 LLM 代码生成）。 然而，还有高效得多的（在数据和计算方面）方式来做符号学习。高出许多个数量级。
正文
If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic learning. In fact what you're doing is specifically a form of DL-guided program synthesis (that's what LLM codegen is).
However there are far more efficient (data-wise and compute wise) ways to do symbolic learning. By many orders of magnitude.
来源：@fchollet · x.com