Switched from ChatGPT to Claude for my daily coding and it actually stuck

I always thought the bigger models were better until I spent 15 minutes debugging code that Claude caught in 2 seconds. Now I swap between them instead of picking one winner. Has anyone else found a use case where a smaller AI beats the flagship?

2 comments

2 Comments

piper91228d ago

Hang on, wait. A smaller model beat the flagship? I've been using Claude for awhile but never bothered with the smaller ones. That's wild, I thought it was all about raw parameter count. Maybe I've been overcomplicating things by always grabbing the biggest option first.

laura_black3128d ago

Raw parameter count" is exactly what I used to chase too, bigger numbers felt safer. But after I spent an hour wrestling with some regex in ChatGPT and Claude nailed it in one shot I completely switched my view. Sometimes the smaller model just gets what you're actually asking without all the extra noise.