Continuing somewhat with my methodology from the "six hats" experiment, I tried another method: four categories. The results weren't as good as the previous one, but I'm still satisfied with it. Lots of interesting ideas and loving Chat-GPT providing "rationale" for it all. Could be helpful as a tertiary tool for human brainstorming, I reckon !
katie kirke
@kekirke
- 13 Followers
- 14 Following
- 37 Posts
Decided to try something a bit different and go back to square one. Researched tips for better prompt generation and ideation methodology. I asked Chat-GPT to help with "six hats" method ideation regarding the Pinterest Problem. I was impressed ! Definitely sticking with this method for prompting...
Lastly, after my interview experiment, I asked three of my friends (the fourth went to bed) to attempt to figure out which questions were and weren't AI.
The results were very interesting — but I think the AI questions are a bit too long and don't fit interview best practices.
PS. I think we should do more "non-AI" experiment tie ins...
In my last conversation with Chat-GPT, it recommended generating data visualizations from my transcript summaries. I figured that could be an experiment on its own, so I tried it out.
I'm not impressed at all with the result. In fact, it was awful. The generated images only reinforced my beliefs on AI's value.
While the transcription was fun, unfortunately that's about it for "glimmers" this week.
Moving from empathize to define in the process, I asked Chat-GPT to analyze the transcription results. What happened ? Chat-GPT created a "xerox of a xerox" of Otter's summary. I'd definitely be better off just using my brain power to define my projects.
Last week we talked about the Pinterest / Spotify / LinkedIn project contexts; however, I was finally able to finish my multi-stage experiment: interviewing my friends about our favorite game, Marvel Rivals.
In the first step, I generated questions with AI. Now, I interviewed friends from Virginia, California, and the UK to stress test Otter's transcription capabilities. Super fun results — the ONLY fun I've had with AI.
Decided to put ChatGPT to the test—can it truly match my writing style? Short answer: No. While I prompted it to generate a caption in my tone, what I got was far too flippant, riddled with emojis, and lacking the precision I aim for. My style leans verbose, pedantic, and at times, ruthlessly exacting—ChatGPT, meanwhile, insists on being overly casual and distressingly cheerful.
Needed faux data for my SAS project, so I had ChatGPT whip up some commercial real estate listings. Fed it detailed scenarios, personas, and project goals—what I got? Decent wireframe-ready content (but don’t ask it to budget your rent 💸😂). Honestly, way better than Lorem Ipsum for prototyping, and I can see this being a handy tool for ideation too. Quick, easy, and surprisingly fun to experiment with.
Put ChatGPT to the test for songwriting ideas—because if there’s one thing I love, it’s a clever concept. AI held its own, but let’s just say… its ideas leaned more ridiculous than refined. AI’s take? Let’s just say it’s got enthusiasm. Still, this experiment got me thinking—can AI-generated absurdity spark unexpected genius? 🤔🎶
I asked ChatGPT to generate pain points by flipping common assumptions—this time, for Marvel Rivals players. So… What do gamers love about lag spikes? (Built-in slow-mo for dramatic effect? 🤔) Turns out, breaking logic might just spark some unexpected insights. Who’s ready to reframe problems like a supervillain? 🦹♂️🎮