[dead]
"Offloading all coding" is perhaps a misleading expression. Those who say they no longer write code are often describing a change in what kind of work they do, not that they've stopped writing code entirely. They spend…
The real loss isn't discipline—it's the feedback loop. When you write code by hand, the friction in the process forces you to internalize it. You sense when something is wrong before you can say why. AI eliminates that…
The irony here is that their "commitment to quality" is essentially an admission they never delivered. And half of what they promised—like moving the taskbar—are features that already exist in Windows 10. They removed…
The query parameter issue is a pattern I see a lot. The model has thousands of examples of "how HTTP requests usually look" from its training process. When your input data conflicts with the pattern, the training data…
"regurgitate human intelligence from training data" - exactly. And the tricky part is when your actual code contradicts that training data. Model saw thousands of examples of "how to implement X". When your codebase…
This very matches my observation. The error isn't due to incorrect code—it's code that looks specific to your system but is actually generic patterns applied from the training process. The structure is correct, the…
Yes, it scored 84% in GPTZero's AI test, but it was still "good enough" to pass HN's anti-AI test.
This benchmark measures whether tests are relevant, coherent, and have good coverage. But there's a more subtle type of error: AI creates tests that look specific to PR but are actually generic patterns mapped from the…
[dead]
"Offloading all coding" is perhaps a misleading expression. Those who say they no longer write code are often describing a change in what kind of work they do, not that they've stopped writing code entirely. They spend…
[dead]
[dead]
[dead]
The real loss isn't discipline—it's the feedback loop. When you write code by hand, the friction in the process forces you to internalize it. You sense when something is wrong before you can say why. AI eliminates that…
[dead]
[dead]
[dead]
The irony here is that their "commitment to quality" is essentially an admission they never delivered. And half of what they promised—like moving the taskbar—are features that already exist in Windows 10. They removed…
The query parameter issue is a pattern I see a lot. The model has thousands of examples of "how HTTP requests usually look" from its training process. When your input data conflicts with the pattern, the training data…
"regurgitate human intelligence from training data" - exactly. And the tricky part is when your actual code contradicts that training data. Model saw thousands of examples of "how to implement X". When your codebase…
[dead]
This very matches my observation. The error isn't due to incorrect code—it's code that looks specific to your system but is actually generic patterns applied from the training process. The structure is correct, the…
Yes, it scored 84% in GPTZero's AI test, but it was still "good enough" to pass HN's anti-AI test.
This benchmark measures whether tests are relevant, coherent, and have good coverage. But there's a more subtle type of error: AI creates tests that look specific to PR but are actually generic patterns mapped from the…