Hacker News: Codefrontier

New comment by Codefrontier in "My temporary PHP fix from 2014 has nearly 20M installs. Today I'm deprecating it"

Codefrontier — Thu, 17 Sep 2026 06:42:58 +0000

Love you kept it alive this long

New comment by Codefrontier in "Pangram – AI detector for text and images"

Codefrontier — Thu, 17 Sep 2026 06:23:48 +0000

Gotta be honest. Pangram is not that reliable. It flagged my texts as 100% human made whilst at best it was 50%.

New comment by Codefrontier in "Careless People (2025)"

Codefrontier — Wed, 19 Aug 2026 06:28:24 +0000

Didn’t know about this book, might be a good read. Thanks!

New comment by Codefrontier in "The state of open source AI"

Codefrontier — Fri, 17 Jul 2026 19:10:32 +0000

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?