You must have really good comprehension and memorizing skill and quick backlog generation to let AI generate as much, since you claim that's not vibe-coding

About "implementing by words bit": I don't believe English is a great language to program.

It's not type-safe, not object oriented, not functional. Has poor tools to highlight syntax or navigate through "wordbase", doesn't fail fast. It has no tests and has too large room for machine or other humans to interpret it.

Very often it's easier for me to express my thoughts in Java, which is ironically known to be a "wordy" language. But it's nowhere close to wordiness of English.

The proponents response is: Natural language (in any language) is much more accessible - almost 100 times more.

I wonder what's going to happen after applying no-review practice, when nobody knows what code-base actually does, in enough details to provide technical guidance?

Consultants will make a mint dealing with these systems. It will make Y2K look like a nothing-burger.

Swans are overrated geese. But ducks are fine

I wonder how codebases for important products (not demos or short-living ones) end up without anyone reviewing the code. Some claim engineers should become more of "architects" and "designers", but not coders/reviewers anymore. Wish to hear people's stories, if much documentation and reviewing from the high-level only is enough to keep the project from becoming a failure

If someone’s best practice,optimization or security check is that important, automate it. Automation is more scalable and consistent . It would make more sense to me to build purpose built agents to look for any patterns that matter. Yes, humans are needed to sanity check and design the agents and rules. Combine that with a well designed build and test harness , human code review seems to me to be obsolete.

Agreed. I don't see that Software Developers must "evolve" from coders to architects, or product owners and if not they disappear due to AI. Small mistakes in the code are the ones that cost the most, and hardest to notice. It's not about how much code someone can generate, but how deep and in details one can understand the code, keeping in mind the big picture.

Happens, sorry for you. I am not good at marketing, and maybe analyzing the market and finding a relevant product to build. So I know the feeling. I'd just use it as a portfolio project to talk about it again once I get a chance: on a job interview, when socializing in professional circles, write articles, etc.

Thanks for the article! Too opinionated imp, but an interesting read.

Claude Pro subscription is just enough for me

I used to be an AI sceptic, but with newer model being released I come closer to the mid: It's a great tool that amplifies human output, but without human judgement in the loop it's a danger to IT systems.

I don't think human should only judge AI design decisions described by LLMs in English. Understanding the codebase is important to be able to judge further development. So reading code, correcting code, articulating on it is still an important skill imo.