I think it's probably a mistake to make a blanket statement that Claude gets every important thing wrong. It's one of those obviously untrue things that makes a skeptical reader question the validity of the rest of the article.

For what it's worth, Opus tells me that I'm wrong and not to do things all of the time. When I reflect on why that is, it's because of the way that I prompt it. You could say that I am subconsciously avoiding setting both me and the LLM to fail in the way the author projects as inevitable.

Specifically, I don't come to it with prompts that resolve cleanly with "tell me how clever I am" replies. I always present myself as a domain expert - because I am a domain expert - and I make it clear when I am open to getting input on the pros and cons of different paths.

With a conclusion that will be unsurprising to any successful LLM daily drivers, this strategy has been remarkably effective.

This literally just happened:

Me: I have two bits and need to mill some 5mm aluminum.

A Makera Spiral 'O' - 1/8" shank * 12mm or a carbide 6.35 * 22 * 50

I believe that they are both carbide single flute bits, but the 2nd one seems like it would make short work of 6061.

Claude: The Makera 1/8" single-flute 12 mm is the sensible choice.

The 6.35 × 22 × 50 mm bit may look like it would make short work of 6061, but on a Carvera it is probably the more dangerous choice. It is a much larger cutter, with much more engagement, and it asks more from the spindle, frame rigidity, workholding, and chip evacuation. In a small dry machine, “bigger” often becomes “more chatter and more heat,” not “faster.”

----

TL;DR: Claude doesn't seem to have any issue telling me when I'm wrong.