AI has made the CLI more important and powerful

"Forty years ago, all successful software boasted a well thought-out GUI and products without one had no chance. Good GUIs provided relief from the cognitive load associated with operating a piece of software, a burden that dropped precipitously as software converged on the same menu items and mouse gestures."

"It couldn't last. The clarity of the classical GUI descended into Rococo flourishes of "ribbons" and "floating panels," a parade of eye candy that brings a sugar crash of confusion. Today we're likely to spend minutes hunting around for a menu option and asking ourselves "It was here last time I looked, did an update take it away?""

"Autonomous agents are now living the same nightmare - as much as a machine can - as we instruct them to use computers on our behalf and they must try to learn about bad GUIs so they can drive them. Agents must snapshot a screen, feed the image into a language model, analyze the results, change the approach they use to attempt executing our desires, and do that repeatedly until they finish whatever task a human set."

Graphical user interfaces revolutionized software by reducing cognitive load through standardized menus and gestures, making software intuitive across products. However, GUI design has deteriorated with excessive visual elements and frequent redesigns, forcing users to relearn interfaces and search for relocated features. This degradation has driven some users away from established software like Final Cut Pro. Autonomous agents now face similar challenges when operating computers on behalf of humans. These agents must repeatedly screenshot screens, process images through language models, analyze results, and adjust their approach to complete tasks. This inefficient process makes GUIs poorly suited for agent interaction, prompting a return to command line interfaces that agents can navigate more effectively.

Read at Theregister