I’ve been playing around with Wolfram Alpha for a couple of days. In all, I agree with Danny’s “impressive” verdict. And it functions in a way that’s very different than any other search engine I’ve ever used. Even beyond impressive, the words that best describe the experience of using Wolfram Alpha are “fun” and “enchanting.”

Wolfram Alpha’s interface allows you to enter queries in natural language. It then tries to disambiguate your query and present relevant facts, charts, illustrations and other supporting “tools.” If it can’t understand your query, you’ll see a “Wolfram Alpha isn’t sure what to do with your input” message, Sometimes it doesn’t have enough information to work with; in these cases you see a “development of this topic is under investigation…” message.

The system also does intelligent things with non-query related information. For example, in calculating distance or physical space, it infers your location (presumably by reading your computer’s IP address) and adjusts numeric or chart/graph data accordingly.

When you’re first starting out using Wolfram Alpha, I’d recommend checking out the hundreds of pre-populated “examples” to see how certain types of queries are best structured. Many of these examples feature structured input fields (for example, weights, measures, dates, and so on) so you can express your question more specifically than with natural language.

Here are some examples showing what Wolfram Alpha can do that would be difficult to impossible to do in Google—or any other search engine, for that matter. You’ll be able to replicate these once Wolfram Alpha is available to everyone; I’m showing screen shots (rather than including links) because I’m working with preproduction test servers rather than the final system set to be launched later today.

I’m also focusing on categories that aren’t traditionally regarded as computationally intensive. Wolfram|Alpha excels at any type of numeric calculation, but it’s also surprisingly good at “computing” information with non-numeric data.