1. Skepticism about replacing human oversight in complex systems
Many experienced engineers argue that for large-scale, multi-developer projects with paying customers, human review and architectural planning remain essential. They contend that AI coding is most effective for smaller, personal projects and that true software engineering requires maintainable, robust code.
- tacker2000: "Thats the problem, the most 'noise' regarding AI is made by juniors who are wowed by the ability to vibe code some fun 'sideproject' React CRUD apps... No mention of the results when targeting bigger, more complex projects, that require maintainability, sound architectural decisions, etc… which is actually the bread and butter of SW engineering and where the big bucks get made."
- tuckwat: "Maybe for a personal project but this doesn't work in a multi-dev environment with paying customers. In my experience, paying attention to architecture and the code itself results in a much more pliable application that can be evolved."
- Ronsenshi: "I'm currently in a strange position where I am being that developer with 15+ years of industry experience managing a project that's been taken over by a young AI/vibe-code team (against my advise)... I assume (or hope?) it would fail to deliver whatever they promised to the CEO."
2. A generational divide in experience and perspective
The discussion highlights a perceived gap between younger developers enthusiastic about AI's potential and veteran engineers with decades of experience on legacy systems. The latter express more caution, citing the complexity of existing codebases and domain knowledge.
- AIorNot: "the OP is a kid in his 20s... How does that compare to those of us with 15-50 years of software engineering experience working on giant codebases that have years of domain rules, customers and use cases etc."
- madrox: "As a guy in his mid-forties, I sympathize with that sentiment... Those giant codebases with years of domain rules are all legacy now. The question is how quickly a new AI codebase could catch up to that code base and overtake it."
3. The future of "vibe coding" and testing over reading code
A forward-looking theme explores a paradigm where developers might no longer need to read or understand the source code, instead defining behavior through tests and letting AI generate the implementation. This idea, often compared to genetic algorithms, is both exciting and controversial.
- tuckwat: "You no longer need to review the code. Or instruct the model at the level of files or functions. You can test behaviors instead."
- asdff: "You generate random code, purely random in raw machine readable binary, and simply evaluate a behavior. Most random generated code will not work. some, however, will work. and within that working code, some will be far faster and this is the code that is used."
- lunar_mycroft: "For this to work, you'd have to fully specify the behavior of your program in the tests. Put another way, at that point your tests are the program. So the question is, which is a more convenient way to specify the behavior of a program: a traditional programming language, or tests written in that language."
4. The challenge of maintaining and debugging AI-generated code
A recurring practical concern is the difficulty of reviewing, debugging, and maintaining code produced by AI agents. This includes the significant effort required to understand code one didn't write and the risks of committing large, unreviewed "slop" to a codebase.
- asdev: "all fun and games until you need to debug the rats nest that you've been continually building. I am actually shocked people who have coded before have been one-shotted into believing this."
- Alupis: "I've also found reviewing LLM generated code to be much more difficult and grueling than reviewing my own or another human's code. It's just a mental/brain drain... Having little or no previous context to understand the code creates a 'standing at the foot of Mt. Everest' feeling constantly, over and over."
- DiabloD3: "Please stop sending PRs to open source projects that are just thousands and thousands of lines of random slop. We're tired of seeing them."