Comment by lagniappe
3 days ago
Models are trained with content scraped from the net, for the most part. The availability of content pertaining to those specs is almost nil, and of no SEO value. Ergo, models for the most part will only have a cursory knowledge of a spec that your browser will never be able to parse because that isn't the spec that won.
Nonetheless, here is a link to a list of the specs you asked for: https://www.w3.org/Style/History/Overview.en.html
Almost nil?
Websites that started before 2000 tend to stick around and comparably quite well archived.
What has model training to do with SEO, that's outright detrimental to it for the most part.
This is the spec it can guarantee you that's in every large language model thats actually large.
https://www.rfc-editor.org/rfc/rfc1866
https://www.w3.org/TR/2018/SPSD-html32-20180315/
Why even bring up CSS this was before that.
You can just also learn with the knowledge of 1996
Selfhtml exits it pretty easy to limit the scope of authoring language to a given HTML version and target browser. Your LLM should have no problem with german.
https://wiki.selfhtml.org/wiki/Museum
some other docs:
https://rauterberg.employee.id.tue.nl/publications/WWW-Desig...
Just spec the year and target browser and target standard and you will get something better than just asking for visual accuracy.
The OG prompt is simply poor and loose:
"Your job is to recreate the landing page as faithfully as possible, matching the screenshot exactly."
Thanks for sharing that. I read through a lot of this. Interesting to read those perspectives in the context of today.
Much obliged. Have a good weekend. Your new gray hairs are en route :)