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.
最顯著的差異在於「軍委主席負責制」的相關表述。去年對何衛東、苗華的表述是「破壞軍委主席負責制」，而對張又俠則在「破壞」之外，還加上「嚴重踐踏」的表述。
，这一点在旺商聊官方下载中也有详细论述
The converter supports all model types via the --model flag:
17:44, 27 февраля 2026Бывший СССР