Never
I had fun with it a dozen times or so when it was new, but I’m not amused anymore. Last time was about a month ago, when someone told me about using chatGPT to seek an answer, and I intentionally found a few prompts that made it spill clear bullshit, to send screenshots making a point that LLMs aren’t reliable and asking them factual questions is a bad idea.
asking them factual questions is a bad idea
This is a crucial point that everybody should make sure their non-techie friends understand. AI is not good at facts. AI is primarily a bullshitter. They are really only useful where facts don’t matter, like planning events, finding ways to spend time, creating art, etc…
Never
I’ve done it once or twice in the early days to see what was up, never since then.
It’s simple: I don’t.
Maybe 1-3 times a day. I find that the newest version of ChatGPT (4o) typically returns answers that are faster and better quality than a search engine inquiry, especially for inquiries that have a bit more conceptualization required or are more bespoke (i.e give me recipes to use up these 3 ingredients etc) so it has replaced search engines for me in those cases.
Once or twice a week
I forgot how the conversation went, but one day, a conversation I had with someone about comprehensibility (which was often an issue) compelled me to talk to an AI, a talk which I remember from the fact the AI did now have such issues as the complaining humans had.
Yeah I’ve run into this a bit. People say it “doesn’t understand” things, but when I ask for a definition of “understand” I usually just get downvotes.
It varies. Sometimes several times a day, sometimes none for a week or two. I’d say about half of those conversations are about software design.
Only to try out the next big upgrade. It will never be human or superhuman.
Once every few months
I mean, if asking to help with code/poorly explained JS libraries counts then… Pretty much every day. Other than that… very rarely.
Multiple times throughout the day. I co-work on personal projects with several different LLMs. Primarily Claude, but also GPT-4o and Llama 70b.
I’ve never tried to have what I would call a conversation, but I use it as a tool for both fixing/improving writing and for writing basic scripts in autohotkey, which it’s fairly good at.
It’s language models are good for removing the emotional work from customer service - either giving bad news in a very detached professional way or being polite and professional when what I want is to call someone a fartknocker.
Maybe 3-4 times a year. Can’t see using it more than that at this point.
