crawshaw - 2025-01-06
This document is a summary of my personal experiences using generative models while programming over the past year. It has not been a passive process. I have intentionally sought ways to use LLMs while programming to learn about them. The result has been that I now regularly use LLMs while working a...
Hasnain says:
Lots to ponder from this piece about using LLMs for day to day productivity.
A few main takeaways for me:
* ensure you can easily verify the output
* getting over the starting hump is really valuable
* having more smaller specialized modules vs fewer larger reusable modules may be better
* use LLMs for tests!
“Let me try to motivate this for the skeptical. A lot of the value I personally get out of chat-driven programming is I reach a point in the day when I know what needs to be written, I can describe it, but I don’t have the energy to create a new file, start typing, then start looking up the libraries I need. (I’m an early-morning person, so this is usually any time after 11am for me, though it can also be any time I context-switch into a different language/framework/etc.) LLMs perform that service for me in programming. They give me a first draft, with some good ideas, with several of the dependencies I need, and often some mistakes. Often, I find fixing those mistakes is a lot easier than starting from scratch.”
Posted on 2025-01-07T03:51:26+0000