alt Hacker News> only a skilled developer who's thinking critically, and comfortable operating at the architectural level, can spot issues in the thousands of lines of generated code, before they become a problem.
An additional factor: to find issues in generated code, the developer has to care. Many developers (especially at big firms) are already profoundly checked out from their work and are just looking for a way to close their tickets and pass the buck with the minimum possible effort. Those developers - even the capable ones - aren't going to put in the effort to understand their generated code well enough to find issues that the agents missed. Especially during the current AI-driven speed mania.
Replies
There are exceptions to this, but in big firms many developers on many teams are actually punished for caring.
You know how some say the big brother sells junk food, then “solutions” to lose weight?
Maybe companies today are being sold junk AI, and next step is being promised “solutions”.. capitalism is working exactly as expected
And by the comments in this section, there’s a lot of them.
Indeed. Generated code is also harder to read because it violates all semantic expectations that rely on the mental model of a human author. A generated piece of code is linguistically plausible but often unknowingly imitates common idioms so incoherently that the actual bug may be accidentally disguised in a way no sane human (even a bad programmer) could have come up with.
Since LLMs have no internal evaluation, as a reviewer one has to account for it and evaluate line by line, rebuild from scratch any hidden rationale and tacit knowledge the LLM didn't have in the first place - only to be mislead into non concerns draining costly hours.
At this point, the investment is often deeper than writing from scratch.