Today we published the Rails reference library, a curated collection of open-source apps meant to serve as an example (for you, LLMs, and anyone new to the community) of production-quality, battle-tested, convention-following Rails applications.
Thank you to @robzolkos for designing and shipping this page.
Read about it here: https://t.co/i3zvAn8aV5
Or check it out for yourself: https://t.co/B0E1oBCFRK
A few months ago we shared a skill for making your app discoverable by LLMs, but does it really work?
We measured two months of server-side LLM traffic to our website to answer the question.
Find out which agents read HTML, which read Markdown, what llms.txt actually does, and the technique that got zero hits:
https://t.co/ekVzyL1CT0
@mattpocockuk would certainly be interesting to see a comparison of outputs of code with different models for the same tasks. Questions is, can you find a scenario that can show the difference or lack of.