I use a model in the app SherpaTTS to read articles from rssaggregator Feedme

Great for giving incantatons for ffmpeg, imagemagick, and other power tools.

“Use ffmpeg to get a thumbnail of the fifth second of a video.”

Anything where syntax is complicated, lots of half-baked tutorials exist for the AI to read, and you can immediately confirm if it worked or not. It does hallucinate flags, but fixes if you say “There is no --compress flag” etc.

I’ve used LLMs to reverse engineer some recipes.

One day I’m going to get around to hooking a local smart speaker to Home Assistant with ollama running locally on my server. Ideally, I’ll train the speech to text on Majel Barrett’s voice and be able to talk to my house like the computer in Star Trek.

Legitimately, no. I tried to use it to write code and the code it wrote was dog shit. I tried to use it to write an article and the article it wrote was dog shit. I tried to use it to generate a logo and the logo it generated was both dog shit and raster graphic, so I wouldn’t even have been able to use it.

It’s good at answering some simple things, but sometimes even gets that wrong. It’s like an extremely confident but undeniably stupid friend.

Oh, actually it did do something right. I asked it to help flesh out an idea and turn it into an outline, and it was pretty good at that. So I guess for going from idea to outline and maybe outline to first draft, it’s ok.

ChatGPT kind of sucks but is really fast. DeepSeek takes a second but gives really good or hilarious answers. It’s actually good at humor in English and Chinese. Love that it’s actually FOSS too

I love fantasy worldbuilding and write a lot. I use it as a grammar checker and sometimes use it to help gather my thoughts, but never as the final product.

I use it for books/movies/music/games recommandations (at least while it isn’t used for ads…). You can ask for an artist similar to X or a short movie in genre X. The more demanding you are the better, like a “funny scifi book in the YA genre with a zero to hero plot”.

I bought a cheap barcode scanner and scanned all my books and physical games and put it into a spreadsheet. I gave the spreadsheet to ChatGPT and asked it to populate the titles and ratings, and genre. Allows me to keep them in storage and easily find what I need quickly.

The image generator to 3D model to animation pipeline isn’t too bad. If you’re not a great visual artist, 3D modeler, or animator you can get out pretty decent results on your own that would normally take teams of multiple people dozens of hours after years of training

LLMs are pretty good at reverse dictionary lookup. If I’m struggling to remember a particular word, I can describe the term very loosely and usually get exactly what I’m looking for. Which makes sense, given how they work under the hood.

I’ve also occasionally used them for study assistance, like creating mnemonics. I always hated the old mnemonic I learned in school for the OSI model because it had absolutely nothing to do with computers or communication; it was some arbitrary mnemonic about pizza. Was able to make an entirely new mnemonic actually related to the subject matter which makes it way easier to remember: “Precise Data Navigation Takes Some Planning Ahead”. Pretty handy.

Getting my ollama instance to act as Socrates.

It is great for introspection, also not being human, I’m less guarded in my responses, and being local means I’m able to trust it.

I’m piping my in house camera to Gemini. Funny how it comments our daily lives. I should turn the best of in a book or something.

Nope. Any use case I have tried with it, I usually find that either a python script, database, book, or piece of paper can always accomplish the same job but usually with a better end result and with a more reliably reproducible outcome.