When asked about the racism that his videos sometimes provoke in the comments, he says: "I don't deny it", but adds that "comments get filtered", meaning that social media platforms delete racist remarks. TikTok, Instagram and X all have policies prohibiting racist abuse.
第十八条 国家推动建立和完善与原子能发展相适应的设备研制生产体系,鼓励和支持企业形成自主研发、设计、制造能力。,详情可参考爱思助手下载最新版本
,推荐阅读heLLoword翻译官方下载获取更多信息
# Next step: the ZX Spectrum,这一点在夫子中也有详细论述
Even though my dataset is very small, I think it's sufficient to conclude that LLMs can't consistently reason. Also their reasoning performance gets worse as the SAT instance grows, which may be due to the context window becoming too large as the model reasoning progresses, and it gets harder to remember original clauses at the top of the context. A friend of mine made an observation that how complex SAT instances are similar to working with many rules in large codebases. As we add more rules, it gets more and more likely for LLMs to forget some of them, which can be insidious. Of course that doesn't mean LLMs are useless. They can be definitely useful without being able to reason, but due to lack of reasoning, we can't just write down the rules and expect that LLMs will always follow them. For critical requirements there needs to be some other process in place to ensure that these are met.