Exactly. Vibe coding is horrible in the wrong hands, but a skilled programmer can utilise it to carry out boring tasks.
If you’re still learning to code, you can’t evaluate the quality of the output, which will result in wild goose chases, wasted hours and tangled low quality scribble code. If you can find and fix the mistakes, you can actually make certain tasks go much faster. Also, don’t let an LLM write more than 20-50 lines at a time. Finding mistakes in longer segments gets very tricky.
If you have a plan in your head, you can request short segments like that. If you let the LLM take care of everything, it’s just going to dump 200 lines, and then you’ll need to rewrite most of it by hand. Gradual step by step approach works well, but it requires constant oversight.
If producing quality code no longer requires skilled programmers, you’re right. As it stands, LLMs produce very raw code that absolutely requires lots of human oversight to qualify as functional.
Nah, I agree with them. All the skilled programmers are getting fired by a bunch of companies with poor financial sense who want to blame everything on AI. Also, if this thread shows anything, then it’s that prospective skilled programmers would rather ask Claude to do their homework for that quick dopamine hit than actually learn that they’re supposed to use parameterized queries so that some random kid’s mom doesn’t delete their production database.
If they figure out a way to refine the slop code with another agent, there will be hardly any need for programmers in the future. We’ll see how that works out.
In the meanwhile, LLMs are being used for cyberattacks and many companies are deploying lots of vibe code everywhere. What could go right…
Exactly. Vibe coding is horrible in the wrong hands, but a skilled programmer can utilise it to carry out boring tasks.
If you’re still learning to code, you can’t evaluate the quality of the output, which will result in wild goose chases, wasted hours and tangled low quality scribble code. If you can find and fix the mistakes, you can actually make certain tasks go much faster. Also, don’t let an LLM write more than 20-50 lines at a time. Finding mistakes in longer segments gets very tricky.
If you have a plan in your head, you can request short segments like that. If you let the LLM take care of everything, it’s just going to dump 200 lines, and then you’ll need to rewrite most of it by hand. Gradual step by step approach works well, but it requires constant oversight.
If things continue as they are, eventually there will be no more skilled programmers.
If producing quality code no longer requires skilled programmers, you’re right. As it stands, LLMs produce very raw code that absolutely requires lots of human oversight to qualify as functional.
Nah, I agree with them. All the skilled programmers are getting fired by a bunch of companies with poor financial sense who want to blame everything on AI. Also, if this thread shows anything, then it’s that prospective skilled programmers would rather ask Claude to do their homework for that quick dopamine hit than actually learn that they’re supposed to use parameterized queries so that some random kid’s mom doesn’t delete their production database.
If they figure out a way to refine the slop code with another agent, there will be hardly any need for programmers in the future. We’ll see how that works out.
In the meanwhile, LLMs are being used for cyberattacks and many companies are deploying lots of vibe code everywhere. What could go right…