A simple rule to follow right now: never trust someone who's selling an AI coding product to tell you how great AI is at coding.
It sounds like my experience has been similar to yours. I have found a few places where agentic coding produces pretty good results.. generally very small patches that could have been written by anyone. I give the tool credit for finding small bugs that nobody noticed before.
On the larger or novel tasks I've thrown at these models, including some of the top tier options, the tools have either produced incorrect solutions, solutions written in a very inefficient way, or solutions that actually introduced more problems. I've taken some of these same challenges to other AI experts as who couldn't believe the tool failed. None of them were able to get good results either.
Everybody is desperate to carve out their slice of the AI Gold Rush right now before it all condenses down and developers realize they can't give up all agency to coding tools trained on the great mass of garbage that's out there. If at some point these tools truly do make developers 10x more efficient, they'll naturally get adopted. Hype chasers and product marketers are not the ones to listen to right now.
Let's take a look at JRuby's startup time journey, all the way up to using JDK 25's AOTCache and Project Leyden features coming to a JDK near you soon.
JRuby 10.0.2 is released! This is a small release to fix an ArgumentError regression in JRuby 10.0.1 plus a few other small fixes. Recommended upgrade for all, but let us know if you run into any issues!
We have just released JRuby 10.0.1.0, our first update to JRuby 10! There's dozens of patches including full support (finally) for Zeitwerk and a bunch of Ruby 3.4 language fixes. Upgrade today and let us know how it goes!
It's finally here! JRuby 10 has been released with support for Ruby 3.4 (including 3.2 and 3.3 updates as well). Minimum Java version has been bumped up to Java 21, allowing us to support more modern JVM features. Check out the release notes and begin your migration today!
It sounds like my experience has been similar to yours. I have found a few places where agentic coding produces pretty good results.. generally very small patches that could have been written by anyone. I give the tool credit for finding small bugs that nobody noticed before.
On the larger or novel tasks I've thrown at these models, including some of the top tier options, the tools have either produced incorrect solutions, solutions written in a very inefficient way, or solutions that actually introduced more problems. I've taken some of these same challenges to other AI experts as who couldn't believe the tool failed. None of them were able to get good results either.
Everybody is desperate to carve out their slice of the AI Gold Rush right now before it all condenses down and developers realize they can't give up all agency to coding tools trained on the great mass of garbage that's out there. If at some point these tools truly do make developers 10x more efficient, they'll naturally get adopted. Hype chasers and product marketers are not the ones to listen to right now.
reply