Well, I've tried using it for the following:

• Asking questions and looking up information in my job's internal knowledgebase, using a specially designed LLM trained specifically on our public and internal knowledgebase. It repeatedly gave me confidently incorrect answers and linked nonexistent articles.

• Deducing a bit of Morse code that didn't have any spaces in it, creating an ambiguous word. I figured it could iterate through the possible solutions easily enough, saving me the time of doing it myself. I gave up in frustration after it repeatedly gave answers that were incorrect from the very first letter.

If I ever get serious about looking for a new job, I'll probably try and have it type up the first draft of a cover letter for me. With my luck, it'll probably claim I was a combat veteran or some shit even though I'm a fat 40-something who's never even talked with a recruitment officer in their life.

Oh, funny story--some of my coworkers at the job got the brilliant idea to use the company LLM to write responses to users for them. Needless to say, the users were NOT pleased to get messages signed "Company ChatGPT LLM." Management put their foot down immediately that doing it was a fireable offense and made it clear that we tracked every request sent to our chatbot.