I’m am a pretty big Star Trek fan. As any good GenXer, I grew up with Star Wars, but I loved and still love the Star Trek universe. It just tickles the nerdier side of my brain.

I love this essay by Patrick Neeman exploring how Star Trek correctly predicted aspects of modern AI.

Neeman:

Star Trek’s track record is a design brief, not a trivia game. The lesson is not that the writers were psychic. It is that they reasoned about interaction and consequence, and those reason forward better than hardware guesses do.

• Design the conversation before the capability. The Trek computer worked as an idea because the interaction model was sound long before the intelligence was. Get the way people ask and receive right first, and let the underlying capability catch up to a surface that already makes sense.
• Treat plain language as a real interface, with real failure states. Natural-language input is not a magic layer that removes design work; it moves the work to disambiguation, confirmation, and recovery. Design what happens when the system mishears as carefully as when it hears.
• Show your seams on translation and transcription by design. These systems are mostly right, which is the dangerous kind of wrong. Surface confidence, make correction cheap, and never present a probabilistic output as settled fact.
• Put the consequence questions in the review, not the retro. If a feature optimizes for a metric, ask early what it does when it optimizes too well. The show’s warnings all came from goals specified narrowly and pursued faithfully.

“Plain language as interface” is happening all around us. We are now coding by using plain language. We’re designing using plain language. The chatbox has been derided as a terrible interface for AI by skeptical designers, including myself. But I think it has staying power precisely because of its support for plain language.