The QWERTY Keyboard was not Designed to be Slow

I need to watch Youtube with an AI LLM to fact check it.

Physicist Brian Keating posted a cosmology interview, and started making a false analogy about keyboard. My AI advises:

While Brian Keating is an astrophysicist and not a historian of technology, he is repeating a very common popular myth. The claim that the QWERTY layout was designed specifically to "slow down" typists is technically incorrect, though it is based on a grain of truth regarding mechanical limitations.

According to historical research into the origins of the typewriter:

The "Jamming" Problem: In early mechanical typewriters, if a typist hit two keys that were physically close to each other in rapid succession, the "typebars" (the hammers that hit the paper) would collide and jam.

The Real Purpose of QWERTY: The layout was designed to separate frequently used letter pairs (like "TH" or "ST") so their physical hammers were on opposite sides of the machine. This allowed the hammers to fall back into place before the next one rose, actually allowing the user to type faster without the machine seizing up.

The "Slow Down" Misconception: The myth likely arose because the layout is not "ergonomically optimal" for modern electronic keyboards. Since we no longer have mechanical hammers to worry about, the QWERTY layout seems unnecessarily difficult compared to alternatives like the Dvorak Simplified Keyboard.

In the video, Keating uses this as an analogy for "technological lock-in", arguing that even if a system is no longer the most efficient, it becomes so widespread that it is nearly impossible to replace—much like he fears is happening with current AI architectures.

The truth is that the qwerty keyboard is not significantly slower than the Dvorak. It just reduces jamming on a mechanical typewriter.

I am wary when some expert tries to make a point using some ridiculous myth that was debunked decades ago. He could have just googled it, and seen that he was wrong.

In the video, Keating shares another classic bit of "technological lock-in" lore, claiming that modern railroad gauges (the distance between the tracks) can be traced back to the width of a Roman chariot, which was designed to fit two horses' butts.

While it’s a great story for a podcast, historians and engineers generally categorize this as a "spurious correlation"—it's mostly a myth, though it has a tiny thread of logic.

The Fact vs. The Fiction

• The Claim: Roman chariots created ruts in European roads. Wagons were built to fit those ruts so they wouldn't break their wheels. Early tramways used those same wagon dimensions, and English trains followed suit, eventually leading to the Standard Gauge (4 feet 8.5 inches) used in the U.S. and much of Europe.

• The Reality: While the standard gauge is roughly the width of an ancient wagon, the specific measurement of 4' 8.5" was actually popularized by George Stephenson, the "Father of Railways." He chose it because it was the width of the existing pre-steam coal tramways in North England where he worked.

• The "Horse's Butt" Part: There is no evidence that Romans measured horses' rear ends to build chariots. Chariots were built to be wide enough to hold two people and stable enough not to tip over. The fact that two horses fit in front of that width is a matter of practical spacing, not a design blueprint that dictated the Space Shuttle's dimensions (another common layer of this myth).

Why Keating Uses It

Keating’s broader point at isn't necessarily about Roman history; he's using it to explain Path Dependence. He argues that once a standard is set—whether it's QWERTY keyboards, railroad widths, or GPU-based AI architectures—it becomes "locked in" because the cost of changing the entire infrastructure is too high, even if a better way exists.

He is probably also wrong with his predictions about AI architectures. He also compares AI to a cockroach, and I think his point is that our AIs could suffer a technological lock-in at a sub-cockroach lever.

I assume that Keating is more accurate when he talks about cosmology experiments. But he says this:

0:30 If you said there's one galaxy, you're stupid. If you said there's one planet, you're stupid. If you said there's one. So why say there's one universe?

I am sticking to one universe. Maybe I am stupid.