Comment by Akamant

It seems like new Holy Wars will rage between those who can afford models like the Opus 4.7 or GPT 5.5 Pro, which in my opinion are unlikely to have been used for anything serious, as they're simply several times more expensive than any human effort. There's a speed advantage (still questionable), and quality isn't guaranteed, but the price completely kills everything. And between those who actually write the code and calculate the development costs. I won't talk about large corporations that can afford it, much less those who develop models. "Mere mortals" simply don't have such opportunities. 17 GoLang microservices for a serious project were written perfectly using the latest version of QWEN. The only areas where we really had to work hard were documentation and a very serious task breakdown. All of this was tested, and yes, a review was required, but everything was within reason. The deadline was 10 days of 24/7 work, including the review. When attempting to submit the same task, Opus 4.7/4.6 had to be stopped after three hours. If you have significant resources for experimentation, you can certainly try. For us, the choice is absolutely clear at this point.