Ofrenda for the Dead Web: an open-weight model writes calaveras for websites that died

说明与用途

该项目通过搜索 API、互联网档案馆和 Gemma 4 模型为已关闭的网站创建祭坛，提取死亡日期、最后的归档页面并生成诗意摘要。

问题

Websites shut down and their content disappears, leaving only archived copies that lack context and narrative.

结果

The tool successfully generated altars for 10 sites, including detailed cards for Friendster, Stadia, Yahoo Answers, Google+, and Vine, with verified death dates, last words, and poetic calaveras.

工作流

• Search for death date and cause using SerpApi or DuckDuckGo.
• Verify the death date and exact words from the search result.
• Query the Internet Archive CDX API for the last good capture before the death date.
• Provide the page text to Gemma 4 to generate site description, last words, and a calavera.
• Verify that the last words appear verbatim in the archived page.
• Build a static HTML altar page with escaped content and safe links.
• Save all data (search results, model outputs, archive captures, checks) to a JSON file for traceability.

证据

An open-weight model found that line on the archived page, and code checked that it was really there, word for word.

来源

The Internet Archive's CDX API takes a to date, so one request returns the last good capture of the home page from before the day it died

来源

Gemma 4 gets the text of that page and returns what the site was, one sentence copied from the page as its last words, and a four-line calavera that may only use facts from the page and the cause of death.

来源

Each run saves everything it saw and said to a JSON file: the search results, every raw model answer, the archive capture, and the result of every check.

来源