> the junior engineer, empowered by some class of LLM tool, who deposits giant, untested PRs on their coworkers—or open source maintainers—and expects the “code review” process to handle the rest.
I'm noticing something else very similar but involving not necessarily junior roles with long messages, when they use these AI writing assistants that resume stuff, creates follow-ups, etc. Putting this additional burden in whoever needs to read it. It makes me think of a quote that says: "I would have written a shorter letter, but I didn't have the time."
I might be mixing the concepts of intelligence and conscience etc, but the human mind is more than language and data; it's also experience. LLMs have all the data and can express anything around that context, but will never experience anything, which is singular for each of us, and it's part of what makes what we call intelligence (?). So they will never replicate the human mind; they can just mimic it.
I heard from Miguel Nicolelis that language is a filter for the human mind, so you can never build a mind from language. I interpreted this like trying to build an orange from its juice.
That looks useful, sometimes when I'm trying to make GPT to do what I want the context of all messages and answers gets too convoluted and it feels the new answers are just stuck in a loop, then I open a new chat. I'm not sure how readable it will be for long answers with code formating, but I'll give a try!
If you're not doing TDD, write the name of the tests before coding.
Why?
* It helps you to understand the problem and the solution;
* I tend to write more test scenarios and cover more cases when I don't need to write the tests right away. I write the names, the actual test it's a problem for my future me;
* You don't have to think and remember of all the scenarios after writing the code, just do what the name says.
* No one actually does TDD lol - jokes a part, TDD might be annoying in some complex cases IMO.
> Most people try quitting their addiction by banning themselves from doing it.
After some failed attempts I quit smoking 7 months a go and this change in the way of thinking made the difference for me. During the failed attempts I used to repeat to myself "I can't smoke", this last time my thought was more like "I don't want to smoke", I didn't even tell to my wife that I was trying to quit so that I would fell less the pressure of being forbidden to smoke. Somehow it worked better for me and whenever I had cravings my thoughts were usually something like "I could smoke if I wanted to, I'm 5 minutes away from a pack of cigarets, but I don't want."
I'm not saying that this was the only factor that made me stop or this is the "secret to quit smoking" or that's easy, it just worked better for me.
This is the basics of Carr's "easy way", right? It basically convinces you that you don't want to smoke. On top of that it specifically doesn't let you stop smoking until you finish the book. So you feel horrible reading this book and smoking until the end when you're like FINALLY I'm allowed to stop!
I'm noticing something else very similar but involving not necessarily junior roles with long messages, when they use these AI writing assistants that resume stuff, creates follow-ups, etc. Putting this additional burden in whoever needs to read it. It makes me think of a quote that says: "I would have written a shorter letter, but I didn't have the time."