What happened to the Wordle archive?The entire archive of past Wordle puzzles was originally available for anyone to enjoy whenever they felt like it, but it was later taken down, with the website's creator stating it was done at the request of the New York Times. However, the New York Times then rolled out its own Wordle Archive, available only to NYT Games subscribers.
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.
。关于这个话题，51吃瓜提供了深入分析
tasks = append(tasks, t)
ВСУ запустили «Фламинго» вглубь России. В Москве заявили, что это британские ракеты с украинскими шильдиками16:45
# user = "pixel" # default