TypeSafe AI 吐槽 cookie 弹窗,问下一个该自动化什么
let's be real, cookie banners were a terrible idea
TypeSafe AI 转发 Lightpanda 将 Jev 嵌入二进制、用 judge() 判断页面是否有真实内容的帖子,并评论称 cookie 弹窗是个糟糕的设计,反问下一个应该被自动化掉的是什么。
查看原帖我们把 Jev 放进了 Lightpanda 二进制文件里,并在其之上构建了 judge()。@typesafeai 再也不用为了发现一个 cookie 横幅而把整个页面发给 LLM 了。 > 被拦截的页面、CAPTCHA、cookie 墙、登录页、付费墙、错误页、空搜索结果以及仍在加载的页面都可能返回 HTTP 200 > judge() 会提出一组预定义问题,告诉你页面是否有真实内容,以及内容类型:文章、列表、产品或文档 > 一次调用,约 0.2 秒 视频中: > 30 个网站,总共约 14 秒 > Lightpanda 在被限流时会退避,接受 cookie 墙,并保留或跳过每个页面
查看原文
We put Jev inside the Lightpanda binary and built judge() on top of it. @typesafeai No more sending a whole page to an LLM just to find out it's a cookie banner. > Blocked pages, CAPTCHAs, cookie walls, logins, paywalls, error pages, empty searches and pages still loading can all return an HTTP 200 > judge() asks a set of predefined questions and tells you if the page has real content, and what kind: article, listing, product or docs > One call, ~0.2s In the video: > 30 sites, ~14s total > Lightpanda backs off when rate-limited, accepts cookie walls, and keeps or skips each page
正文
let's be real, cookie banners were a terrible idea
what should get automated away next?