zlacker

[return to "My AI skeptic friends are all nuts"]
1. bloat+j2[view] [source] 2025-06-02 21:25:27
>>tablet+(OP)
So we replace the task of writing tedious boilerplate with the task of reading the AI's tedious boilerplate. Which takes just as long. And leaves you with less understanding. And is more boring.
◧◩
2. Philpa+s3[view] [source] 2025-06-02 21:30:51
>>bloat+j2
You are either a very fast producer or a very slow reader. Claude and Gemini are much faster at producing code than I am, and reviewing their code - twice over, even - still takes less time than writing it myself.
◧◩◪
3. seadan+f7[view] [source] 2025-06-02 21:52:05
>>Philpa+s3
Reviewing code is often slower than writing it. You don't have to be an exceptionally fast coder or slow reviewer for that to be true.
◧◩◪◨
4. thegeo+sd[view] [source] 2025-06-02 22:31:46
>>seadan+f7
If this was the case, regular code review as a practice would be entirely unworkable.
◧◩◪◨⬒
5. seadan+lk[view] [source] 2025-06-02 23:13:21
>>thegeo+sd
Interesting point! I'd like to explore this a bit more.

Would you mind going into a bit more specifics/details on why regular code review practice would become unworkable, like which specific part(s) of it?

[go to top]