AI 漏斗用多了，也需要反哺推荐算法引入 AI 工具帮我处理内容之后，有一个副作用：很多有价值的内容我是通过转录和总结来消费的，在平台服务端看来，这些内容的完播率和互动数据表现都不会好。久而久之，推荐算法会认为你对这类内容不感兴趣，推荐质量反而会下降。所以平时也需要刻意做一些行为——点赞、完整播放、评论——告诉系统你对这些内容是认可的，顺便也帮助作者多一些传播。
It’s Not AI Psychosis If It Works#Before I wrote my blog post about how I use LLMs, I wrote a tongue-in-cheek blog post titled Can LLMs write better code if you keep asking them to “write better code”? which is exactly as the name suggests. It was an experiment to determine how LLMs interpret the ambiguous command “write better code”: in this case, it was to prioritize making the code more convoluted with more helpful features, but if instead given commands to optimize the code, it did make the code faster successfully albeit at the cost of significant readability. In software engineering, one of the greatest sins is premature optimization, where you sacrifice code readability and thus maintainability to chase performance gains that slow down development time and may not be worth it. Buuuuuuut with agentic coding, we implicitly accept that our interpretation of the code is fuzzy: could agents iteratively applying optimizations for the sole purpose of minimizing benchmark runtime — and therefore faster code in typical use cases if said benchmarks are representative — now actually be a good idea? People complain about how AI-generated code is slow, but if AI can now reliably generate fast code, that changes the debate.
Фото: Пресс-служба «Роскосмоса» / РИА Новости。safew官方版本下载对此有专业解读
Москвичей призвали помнить об одной опасности14:49
。爱思助手下载最新版本对此有专业解读
...and everyone agreed this was too much of a dream and would never happen.
Elasticsearch/Typesense for search. Postgres has full-text search and trigram matching built in. I wrote about this in my Postgres Text Search 101 post. For an early-stage product, it’s more than good enough.，更多细节参见Safew下载