Is Wolfram Alpha too clever by half?

An excellent and exhaustive survey of Wolfram Alpha by Mencius Moldbug. I think he thinks like I do: an engineer that looks at user interface analytically.

That’s not as bad as it sounds. I have no visual design abilities myself, yet I know something about interface. It has to do with expectations.

MM’s critique is that Wolfram Alpha is a great tool with a fundamental mistake in its interface. The mistake is that it makes a promise it can’t achieve: For serious UI geeks, one way to see an intelligent control interface is as a false affordance — like a knob that cannot be turned, or a chair that cannot be sat in. The worst kind of false affordance is an unreliable affordance — a knob that can be turned except when it can’t, a chair that’s a cozy place to sit except when it rams a hidden metal spike deep into your tender parts.

Wolfram’s natural-language query interface is an unreliable affordance because of its implicit promise of divine intelligence. The tool-guessing UI implicitly promises to read your mind and do what you want. Sometimes it even does. When it fails, however, it leaves the user angry and frustrated — a state of mind seldom productive of advertising revenue.

The impedance mismatch is that Wolfram Alpha is a hard-data tool hidden behind a fuzzy-logic interface. It will work sometimes, but not always.

WA is brittle because the set of inputs it can understand is finite and well-defined; users’ desires are not.

Google works because both the input and the output are fuzzy. The searcher is human; the search results are also human. Thus, ambiguity by the searcher has a good chance of matching the ambiguity of the search results.

WA’s search results (its underlying databases) are not ambiguous. Yet it implies to its users, via its natural-language interface, that they can submit their requests in ambiguous ways. This is a fake-out on WA’s part: by handling many permutations of user inputs, it creates a illusion of fuzziness. When the illusion fails, the harm is great.

Thus, WA will need to handle an ever-expanding set of specific inputs from users. Mencius Moldbug thinks this race is unwinnable. His suggestion? Be honest: But if you are an actual flow user who actually needs to get something done, WA could give you an alternative, manual interface for selecting your tool. You might perform the discovery task by browsing, say, a good old-fashioned menu. For example, the Nutrition Facts tool might come with its own URL, which you could bookmark and navigate to directly. There might even be a special form for entering your recipe. Yes, I know none of this is very high-tech.

Read the whole thing. Then, read this book. :)