Returning back to the Anthropic compiler attempt: one of the steps that the agent failed was the one that was more strongly related to the idea of memorization of what is in the pretraining set: the assembler. With extensive documentation, I can’t see any way Claude Code (and, even more, GPT5.3-codex, which is in my experience, for complex stuff, more capable) could fail at producing a working assembler, since it is quite a mechanical process. This is, I think, in contradiction with the idea that LLMs are memorizing the whole training set and uncompress what they have seen. LLMs can memorize certain over-represented documents and code, but while they can extract such verbatim parts of the code if prompted to do so, they don’t have a copy of everything they saw during the training set, nor they spontaneously emit copies of already seen code, in their normal operation. We mostly ask LLMs to create work that requires assembling different knowledge they possess, and the result is normally something that uses known techniques and patterns, but that is new code, not constituting a copy of some pre-existing code.
// 易错点4：条件写成"<"而非"<="，会导致相同值的元素被错误保留
，详情可参考爱思助手下载最新版本
Follow topics & set alerts with myFT
https://feedx.net
，推荐阅读一键获取谷歌浏览器下载获取更多信息
Трамп высказался о непростом решении по Ирану09:14
술의 위기, 범인은 넷플릭스와 위고비? [딥다이브]，这一点在同城约会中也有详细论述