Maybe it is because I started out in QA, but I have to strongly disagree. You should assume the code doesn't work until proven otherwise, AI or not. Then when it doesn't work I find it is easier to debug you own code than someone else's and that includes AI.
zbyte64
joined 1 year ago
Why would you ever yell at an employee unless you're bad at managing people? And you think you can manage an LLM better because it doesn't complain when you're obviously wrong?
A junior developer actually learns from doing the job, an LLM only learns when they update the training corpus and develop an updated model.
It’s usually vastly easier to verify an answer than posit one, if you have the patience to do so.
I usually write 3x the code to test the code itself. Verification is often harder than implementation.
DOGE has entered the chat
When LLMs get it right it's because they're summarizing a stack overflow or GitHub snippet it was trained on. But you loose all the benefits of other humans commenting on the context, pitfalls and other alternatives.
Pepper Ridge Farms remembers when you could just do a web search and get it answered in the first couple results. Then the SEO wars happened....
I call it colonial trauma. Our forefathers would rape the help and the worse that would happen is getting berated by the judge.
As we say in the USA:
"The police don't protect us, we protect us"
But no one should buy the premise here, because it is so ugly. That premise is that people have fixed racial identities, and these categories are strict. The most disturbing line in the article is this righteous bit—“asked if any of his family had intermarried while in East Africa, he said in the interview on Thursday, ‘They’re all of Indian origin, from Gujarat.’”
Just a damn good point that race is not set in stone but dynamic. Haven't seen this point until now.
Padme: you are going to release the video footage, right?
That's because "The market can remain irrational longer than you can remain solvent."