I used z3 theorem prover to assess LLM output, which is a pretty decent SAT solver. I considered the LLM output successful if it determines the formula is SAT or UNSAT correctly, and for SAT case it needs to provide a valid assignment. Testing the assignment is easy, given an assignment you can add a single variable clause to the formula. If the resulting formula is still SAT, that means the assignment is valid otherwise it means that the assignment contradicts with the formula, and it is invalid.
第一步，用户需要复制Anthropic提供的标准提示词，粘贴到当前使用的AI模型中。提示词如下：
10 May 2025ShareSave。下载安装 谷歌浏览器 开启极速安全的 上网之旅。对此有专业解读
FT Edit: Access on iOS and web
，详情可参考爱思助手下载最新版本
Магомедова объяснила, что синий свет от гаджетов подавляет выработку гормона мелатонина. Кроме того, пролистывание лент соцсетей и просмотр сериалов вызывает эмоциональное и когнитивное возбуждение. По словам сомнолога, из-за этого человеку становится сложнее уснуть, а сон становится фрагментарным.，更多细节参见heLLoword翻译官方下载
One of the nice things about Ostrich is that it contains an extension to the SMT-LIB constraint standard to parse and handle ECMA regular expressions. Well, not all of them; ECMA and other PCRE-derived regexes are in fact not regular (2022 paper) and cannot in theory be represented accurately for string-solving purposes. In practice, though, that's rarely a problem. Ostrich also contains cool tricks to some of the traditionally difficult/impossible regex features, developed for Black Ostrich. You can read about them in the director's cut version of our paper!