I just wrote an internal report in my company.
My conclusion from the project I'm working on is that, as of this day, there is no way to have both this so-called 20x performance improvement _and_ any kind of quality. Or security if whoever is running the agent has any token in an .env anywhere on the same file system.
We'll see in which direction the CTO takes this. My bet is not on quality.
The company I work for, the code Opus 4.8 is able to generate, is higher quality than what was left behind by 10+ years of contractors that have come and gone.
I understand that some developers produce very poor code. Maybe in some companies it's the norm. Luckily for me, I've seldom worked alongside such developers.
In my company, the code Opus 4.8 is able to generate appears competent, but if you dig a bit, it contains way more timebombs than anything I've seen the team members develop.
Time bombs and just 2-3x the amount of code for the same thing. I recently rewrote a Claude generated feature from 3000 lines to 800. I guess AI fans are just predicting that no one will have to read the code in the future or something like that.
Yeah, I suspect the 2-3x amount of code, but I can't prove it yet. This will wait for the next report :)
Last study I read said it was 6x.