Show HN: 500 clocks in one 6.3 MB HTML file by Opus 5.5
来源:Hacker News 首页收录:2026/10/18
✦ AI 解读
作者用前沿模型生成自包含时钟网页来测试模型能力,类似 Simon Willison 的“鹈鹕骑自行车”指标。Claude Opus 5.5 生成的时钟在多样性、趣味性和质量上表现突出,作者通过多轮对话让其生成了 500 个时钟,并汇总在单个 6.3 MB 的 HTML 文件中。项目已在 GitHub 开源,包含提示过程和页面设计说明。
Lately I've been testing frontier models by having them create self-contained web pages that display clocks--sort of my personal version of Simon Willison’s pelican-on-a-bicycle metric.I have been particularly impressed by the variety, interest, and quality of the clocks created by Claude Opus 5.5. Over the course of several sessions in the Claude chat interface, I had it build a total of 500 clocks.Claude’s summary of the prompting process and page design is here:https://github.com/tkgally/500-clocks/tree/main
Comments URL: https://news.ycombinator.com/item?id=50137820
Points: 11
# Comments: 2
相关推荐
Kimi K3.1 Pro and K3.1 Pro Highspeed
✦ AI 摘要月之暗面(Moonshot AI)在 Kimi Code 文档中上线 Kimi K3.1 Pro 与 K3.1 Pro Highspeed 两个模型版本,前者主打高质量代码生成,后者面向低延迟高速推理场景。该消息在 Hacker News 引发 169 点、79 条评论讨论,从业者关注其代码能力、定价与高速版的实际吞吐表现。
Kimi K3.1 Pro and K3.1 Pro Highspeed
✦ AI 摘要Kimi 发布 K3.1 Pro 与 K3.1 Pro Highspeed 两款模型,官方文档页面已上线,并在 Hacker News 引发讨论(86 分、21 条评论)。Highspeed 版本推测主打低延迟推理,适合对响应速度敏感的编码等场景。目前公开信息有限,具体参数、基准评测与定价尚未披露,建议关注官方后续更新。
Gemma-4-26B-A4B with 39-69% less thinking at same accuracy
✦ AI 摘要Hacker News 上分享的一篇文章介绍 Gemma-4-26B-A4B 模型,声称在保持相同准确率的前提下,将思考(推理)过程减少了 39% 至 69%。该内容来自个人博客 bottlecapai.com,讨论热度较低(3 分、0 评论),但涉及大模型推理效率优化这一从业者关注的方向,具备一定参考价值。