Should we understand code written by AI? A developer's worry about speed and quality(mobtown.jp)
Writing language: KoreanRead in the original language
Plain summary
- This is a piece by a developer who has believed that people should understand and modify the output themselves, and who is now rethinking their way of working as generative AI increasingly builds and fixes programs.
- The author feels that the quality difference between people who submit AI-generated code as is and people who submit it after understanding it is not clearly visible from the outside. This is the author's personal experience and opinion.
- The author asks who would be rewarded: a person who produces 3 results worth 70 points in the same time, or a person who produces 1 worth 90 points. The scores are a hypothetical example to explain the choice between speed and quality.
- The author sees a trend of leaving everything to AI, from deciding which features a program should have to development, testing and maintenance. The author points out that once a product is released, development may be judged a success regardless of usability.
Editorial opinion
O: If you are a team lead reviewing code written by AI, I suggest setting, before release, the scope that the person in charge can understand and explain.
X: The author assumes a situation where, in the same amount of time, you produce three items worth 70 points and one item worth 90 points. The scores are not actual measurement results. They represent the contrast between speed and quality.
Writing language: Korean
Found on
はてなブックマーク テクノロジー ↗ / Published by source
Have you run into something like this? Tell us in a line or two what you did. You do not need to know the product.