Had a tough choice between GPT-4 and Claude for my coding project

I was building a small web app last month and needed help debugging some messy JavaScript. Most people online were pushing GPT-4 hard, saying it was unbeatable for code. I tested both on the same broken function, a 50-line mess with nested loops. Claude caught the issue in two tries while GPT-4 gave me three different wrong fixes before I gave up. Anyone else find a specific AI that just clicks better for real work?

2 comments

2 Comments

jamienguyen16d agoMost Upvoted

Yeah that "confident but useless" thing is real. It's like how my GPS once told me to drive through a closed road and then acted like it was my fault. I've noticed a bigger pattern outside of AI too. Like when I ask a hardware store employee for help and they just point at a random aisle vs the one guy who actually walks you over and checks the part numbers. Same with doctors sometimes. Some are quick to say "it's nothing" while others actually listen and find the real problem. So it's not just AI. Some systems or people are built to sound correct instead of being correct.

diana_king16d ago

That nested loop problem sounds brutal, and I've had almost the exact same experience with GPT-4 giving confident but useless answers before Claude nailed it on the first pass.