As much as my first gut reaction to this article was to be excited about its conclusion, I can’t say my experience matches up. Are LLMs perfect? Absolutely not, but I can point to many examples in my own work where using Codex has saved me easily a week or more—especially when it comes to tedious refactors. I don’t agree with the conclusion; the real-world improvement and progress I’ve seen in the last year in the problem-solving quality of these agents has been pretty astounding.
The reason for my excitement about the conclusion is obvious: I want programmers and people to stay in demand. I find the AI future to be quite bleak if this tech really does lead to AGI, but maybe that’s just me. I think we’re at a pretty cool spot with this technology right now—where it’s a powerful tool—but at some point, if or when it’s way smarter than you or me… I'm not sure that's a fun happy future. I think work is pretty tied to our self worth as humans.
Sure thing. I work on a few projects for my company. The main one is an Android and iOS audiobook-media-player app. I had to update the Android side to use the Google Media3 library instead of the legacy ExoPlayer library. In a typical app this would be pretty straightforward, but we’ve mixed in a lot of custom elements that made the transition quite challenging. I actually attempted it manually back in the day and probably spent three or four days on it, but I simply didn’t have time to finish, so I shelved it. A few months ago I tried again in Codex; within two prompts it was done flawlessly and starting from the beginning.
Another example: I also maintain the back-end API for these apps. There was a lot of old utility code that was messy, unorganized, and frankly gross. I had Codex completely reorganize the code into a sensible folder structure and strip out any functions that weren’t being used anymore—something like 300-plus functions. Doing that by hand would easily have taken a day or more
I could go on, but those were the two initial “aha” moments that showed me how powerful this tool can be when it’s used for the right tasks.
Not the OP but I just got done with a codebase-wide re-architecture (driven by a need for a complex data migration) in a little ~2.5 weeks. 800+ files changed, 60k+ line diff.
Without AI it would have taken me several months, and that is only if I managed to avoid burnout. The vendor quotes we got just to see if we could outsource the work were all six figures.
Ya migrated about 50% of a code base to a new architecture from a legacy architecture. I've seen a massive speed improvement in my app since doing this and significantly less bugs. The code base is probably on the order of 150,000 lines of code or so. This refactor took about a week with AI... this would have taken easily a month or more if I did this myself. I also had AI write me a bunch of tests that never before existed in this codebase. Obviously these tests aren't perfect, but neither would mine be if I wrote them by hand.
> Any decent IDE can do that refactoring instantly.
its an interesting point that got me thinking: at what point does all of this just boil down to dev ux/ide features, and does this need to run on the server (as economic rents) vs just locally?
> Any decent IDE can do that refactoring instantly.
The refactoring? Sure. But IDEs don't read your code and logically categorize it into folders. From what I understand, they are saying that they outsourced the thinking part as well.
The reason for my excitement about the conclusion is obvious: I want programmers and people to stay in demand. I find the AI future to be quite bleak if this tech really does lead to AGI, but maybe that’s just me. I think we’re at a pretty cool spot with this technology right now—where it’s a powerful tool—but at some point, if or when it’s way smarter than you or me… I'm not sure that's a fun happy future. I think work is pretty tied to our self worth as humans.