Comprehension Debt: The Hidden Cost of AI-Generated Code(oreilly.com)
oreilly.com
Comprehension Debt: The Hidden Cost of AI-Generated Code
https://www.oreilly.com/radar/comprehension-debt-the-hidden-cost-of-ai-generated-code/
3 comments
Yes, this one is true. Most of the orgs focus on delivery but keep forgetting what they are losing.
The verification of the software is most important aspect and we do not have any solid way to do that using AI. The loss of comprehension and context makes the developer to have blind spots and it would show in the degrading quality of software as we move forward.
This is something about human outlook that AI could not replicate.
The verification of the software is most important aspect and we do not have any solid way to do that using AI. The loss of comprehension and context makes the developer to have blind spots and it would show in the degrading quality of software as we move forward.
This is something about human outlook that AI could not replicate.
well written. finally someone mentioned that a human operator that has the full architecture context is needed. that i think is the role of human in coding in future.
but i will argue one thing though. the spec approach is good enough with the current model capability. it is the matter of scoping. if you scope the spec correctly and granular enough, the agent will produce replicable implementation. and if i am to look into future, as model capabilities advances, the spec approach will be better and better, allowing for larger spec scope to be implemented at once
but i will argue one thing though. the spec approach is good enough with the current model capability. it is the matter of scoping. if you scope the spec correctly and granular enough, the agent will produce replicable implementation. and if i am to look into future, as model capabilities advances, the spec approach will be better and better, allowing for larger spec scope to be implemented at once
As a Senior IC, the amount of code I have to review every single day has dramatically risen.
Interestingly, so is the confidence of the junior engineers putting that code up for review, because another AI has reviewed the code already.
Not sure, but if this is how things pan out, we are looking at severely degraded softwares shipping to customers, very very soon