I’m not even going to bother commenting on that train wreck of a post, but I just wanted to mention that I hate the writing style of programming-related LinkedIn posts. They’re just chock-full of sweeping generalizations presented as absolute truth in an extremely patronizing tone.
Why can’t people just say, “In my opinion, X technology is a better fit for Y situation for Z reason,” instead of “Every time you encounter X, you must do Y, otherwise you’re dead wrong.”
It’s just simultaneously so arrogant and also aggressively ignorant. If someone spoke to me like that in real life, I would never want to speak with them again. And these people are broadcasting this shit to their entire professional network.
I know this comes from a good place, but you are misunderstanding how LLMs work at a fundamental level. The LLMs “admitted” to those things in the same way that parrots speak English. LLMs aren’t self-aware and do not understand their own implementation or purpose. They just spit out a statistically reasonable series of words from their dataset. You could just as easily get LLMs to admit they are an alien, the flying spaghetti monster, or the second coming of Jesus.
Realistically, engaging with these LLMs directly in any way is not really a good idea. It wastes resources, shows engagement with the app, and gives it more training data.