23
Switched from GPT-4 to Claude 3.5 for my code reviews last month
The feedback went from generic suggestions to actually catching my variable naming issues - has anyone else noticed a big difference between models for debugging?
2 comments
Log in to join the discussion
Log In2 Comments
the_emma9d ago
It goes deeper than just code reviews honestly. Lately I've noticed this pattern everywhere - like how AI writing used to all sound like the same boring corporate memo, but now some of them actually have personality. It's like we're watching them grow up in real time. Claude specifically has this way of catching things that feel human, like when you're on autopilot and naming things "temp1" and "temp2" lol. Makes me wonder if the future is just gonna be picking which AI fits your vibe instead of which one is "smarter".
7
Used to think people were exaggerating, but yeah, Claude caught my lazy variable names too.
1