Live data from Hacker News

Viewing profile — thienannguyencv

thienannguyencv

HN member
Joined
Fri, Mar 20, 2026, 3:23 PM UTC
HN karma
5
Public activity
19 items

About thienannguyencv

No profile information was provided.

Recent public activity

  1. comment
  2. comment
    Comment #47512357

    "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 sto…

  3. comment
  4. comment
  5. comment
  6. comment
  7. comment
  8. comment
    Comment #47505009

    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 befo…

  9. comment
  10. comment
  11. comment
  12. comment
  13. comment
    Comment #47465961

    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 alre…

  14. comment
    Comment #47464398

    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 conflict…

  15. comment
    Comment #47463904

    "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 …

  16. comment
  17. comment
    Comment #47456495

    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 proc…

  18. comment
    Comment #47456338

    Yes, it scored 84% in GPTZero's AI test, but it was still "good enough" to pass HN's anti-AI test.

  19. comment
    Comment #47455949

    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 act…