Поводом для критической статьи послужило обнародование официальных результатов экспертизы аварии, которая произошла в городе Чэнду в октябре минувшего года. Установлено, что водитель не смог покинуть салон горящего автомобиля из-за дверных ручек.
AFP via Getty Images
，更多细节参见旺商聊官方下载
第一百零二条 为了查明案件事实，确定违反治安管理行为人、被侵害人的某些特征、伤害情况或者生理状态，需要对其人身进行检查，提取或者采集肖像、指纹信息和血液、尿液等生物样本的，经公安机关办案部门负责人批准后进行。对已经提取、采集的信息或者样本，不得重复提取、采集。提取或者采集被侵害人的信息或者样本，应当征得被侵害人或者其监护人同意。
During development I encountered a caveat: Opus 4.5 can’t test or view a terminal output, especially one with unusual functional requirements. But despite being blind, it knew enough about the ratatui terminal framework to implement whatever UI changes I asked. There were a large number of UI bugs that likely were caused by Opus’s inability to create test cases, namely failures to account for scroll offsets resulting in incorrect click locations. As someone who spent 5 years as a black box Software QA Engineer who was unable to review the underlying code, this situation was my specialty. I put my QA skills to work by messing around with miditui, told Opus any errors with occasionally a screenshot, and it was able to fix them easily. I do not believe that these bugs are inherently due to LLM agents being better or worse than humans as humans are most definitely capable of making the same mistakes. Even though I myself am adept at finding the bugs and offering solutions, I don’t believe that I would inherently avoid causing similar bugs were I to code such an interactive app without AI assistance: QA brain is different from software engineering brain.