Codefrontier
Re:I paid people to try and follow my README
on Sunday October 11, 2026 @10:00AM (#50043387)
So usability testing?
Re:My temporary PHP fix from 2014 has nearly 20M installs. Today I'm d...
on Thursday September 17, 2026 @02:42AM (#49737205)
Love you kept it alive this long
Re:Pangram – AI detector for text and images
on Thursday September 17, 2026 @02:23AM (#49737084)
Gotta be honest. Pangram is not that reliable. It flagged my texts as 100% human made whilst at best it was 50%.
Re:Careless People (2025)
on Wednesday August 19, 2026 @02:28AM (#49357661)
Didn’t know about this book, might be a good read. Thanks!
Re:Mozilla: The state of open source AI
on Friday July 17, 2026 @03:10PM (#48951137)
I agree with your speculation to be honest. And yet I’ve tried several local open weights model now and none gives the same quality of answers as Claude gives me on a regular Sonnet model. Mind you: I am “running” 48GB of RAM so I can’t try every model. Where does this difference come from? Can we actually get close locally?