AI blog posts are all dancing to the same tune

Blogging isn’t my main focus – documentation, developer experience, and information architecture is. That said, I’m happy to help out my client Sensible with some blog content, since I’m extremely well positioned to do so.

To that end, recently I was researching competitors’ blog content for Sensible. I searched on a particular blog post theme title (I googled “Highs and lows of extracting data from bank statements”, if you’re interested). I was surprised by how many of the top search results were obviously (to my eye) AI generated, and how similar they all were. Aside from being uniformly generic and high level, they contained sometimes the same headings and bullet points with minor variations. They were even the same at the level of specific phrases. “In today’s data-driven world…” showed up in the introductions more times than I could count. It strongly reminded me of the conman who sells the same “spirit fingers” choreography to competing cheerleaders in the 2000 movie Bring It On. Everyone’s been sold the same song and dance!

Anyway, I’m currently preparing to write a new series of AI-assisted blog posts for this client, and as always, I think the way to actually provide value to the reader is to ground the post in specific details. In my last series, the specifics were in the hand-written code samples and the comments the AI generated for those samples. This time around, the specific will be in transcribed interviews I conduct with our CSE team: so we can tell real (anonymized) implementation stories, with all their highs and lows.