DevonThink: how to increase the serendipity?

What did you read that created the expectation that DEVONthink would look at your data and add to your knowledge? Their advertising is somewhat misleading:

DEVONthink Help
The See Also & Classify inspector is the main interface to DEVONthink’s brain, our built-in AI engine. This engine is analyzing the contents and locations of all documents in your database and making connections between them. These connections can be seen in this inspector pane.

I’ve always objected to their use of “AI” – it is only a marketing term. Not “real” AI.

What DEVONthink actually does is look at a corpus of documents, extract a concordance of words, keep a running calculus of word frequency, look at the links you (not the software) created, the tags you (not the software) added, etc. It then simply makes mechanical suggestions based on word frequency and the other factors – basically telling your in the “See Also” display that “this document is ‘similar’ to these other documents”.

That is not knowledge. It’s a contextual analysis algorithm that is similar to “red things look like cherries”. DEVONthink can mechanically suggest relationships, but the knowledge-building can only be done by the user. Serendipity happens when chance connections between words (the only thing DEVONthink has) spark an idea in you, and you pursue it further than the software can take it.

Years ago a DEVONthink employee, now deceased, Bill DeVille wrote extensively in their forum about his use of the DEVONthink AI. Bill once wrote this advice, that I think might be helpful in framing an understanding of what DEVONthink can do for you:


Bill DeVille 12/4/2007
See Also is probably “smarter” than you think. It’s forte is finding similarities of words and especially the contextual relationships among words in a collection of documents. No, See Also doesn’t look at Names or at the group locations of documents (although classification may help you, the human part of the interactive team, organize your own thought).

Let me give an example. Dogs are canines. So are wolves, foxes and coyotes. Suppose you are viewing an article about dogs, which doesn’t include the term “canine”. You invoke See Also and find that the list includes an article about wolves, even though the term “dog” doesn’t appear in that article about wolves. How did that happen? Somewhere in that database is a “bridge” document that includes the term “canine” as related both to dogs and to wolves. The greater the number of such “bridge” documents, or the greater the frequency with which the relationship is defined even in a single “bridge” document, the more likely See Also is to make such a connection. [Emphasis added]

Take that as a tip. You are trying to force a connection among documents by grouping them. The connection may be the concept of stoichiometry, but that term doesn’t exist in many of the documents in your collection. One way to enhance the behavior of See Also to make that connection would be to make sure there’s one or more documents in the collection that “bridge” the term “stoichiometry” to other terms or word patterns common to the concept. That bridge document might be a beautifully written overview of the field, or it might be a “nonsense” document that is basically a glossary of related terms, perhaps repeated for emphasis.

I still do organization, at least to some degree, of my database collections for my own benefit. I can’t create and hold in my mind tables of all the tens of millions of words in my database and also the patterns in which those words occur, like See Also. But my database isn’t trained as a chemist, or ecologist, or economist or whatever my interests may be. So I’m responsible for determining the pertinence of documents suggested by See Also. Some of those suggestions may be “dumb” while others are “brilliant” – it’s up to me to make the distinction. This is human/machine interaction, and I often find it very useful.

Sometimes I find it useful to follow a trail of See Also suggestions. Perhaps the first list of suggestions may not give me what I’m looking for; but selection of a document from that list and another invoking of See Also may lead me to discovery of a relationship I hadn’t thought of.

(DEVONthink in 2021 is very close to DEVONthink in 2007, as far as See Also is concerned. So the advice still stands.)

11 Likes