Comment by nottorp
7 days ago
Here's a rl example from today:
I asked $random_llm to give me code to recursively scan a directory and give me a list of file names relative to the top directory scanned and their sizes.
It gave me working code. On my test data directory it needed ... 6.8 seconds.
After 5 min of eliminating obvious inefficiencies the new code needed ... 1.4 seconds. And i didn't even read the docs for the used functions yet, just changed what seemed to generate too many filesystem calls for each file.
Nice, sounds like it saved you some time.
You "AI" enthusiasts always try to find a positive spin :)
What if I had trusted the code? It was working after all.
I'm guessing that if i asked for string manipulation code it would have done something worth posting on accidentally quadratic.
Depends on how toxic the culture is in your workplace. This could have been an opportunity to "work" on another JIRA task showing 600% improvement over AI generated code.
3 replies →
> What if I had trusted the code? It was working after all.
Then you would have been done five minutes earlier? I mean, this sort of reads like a parody of microoptimization.
6 replies →
Why would you blindly trust any code? Did you tell it to optimize for speed? If not, why are you surprised it didn't?
6 replies →