I see this old work project of mine contains the files "prototype" and "prototype (non idiotic version)".
Distressingly, I can't see a problem with the first one.
I see this old work project of mine contains the files "prototype" and "prototype (non idiotic version)".
Distressingly, I can't see a problem with the first one.
@pozorvlak It matches my experience that chatgpt's image generation is bad at diagrams. I've played with juggling patterns and hobby circuit design: clearly explained in text, nonsense diagrams.
Uninformed guess: text is produced linearly, every token chosen in context of what's already written, creating coherent ideas. Vs images generated all at once, so lots of plausible-looking initial ideas all presented together with no checking whether they make sense in context?
In day 3 of this now, and people are openly trolling. Overnight someone suggested "if you want to unsubscribe, simply reply-all with STOP" and so far twenty people have. Someone else said "for your convenience, I asked Copilot to summarise this email thread" and pasted the output which helpfully suggests "action: review and correct the mailing list membership".
This is a small beacon of untrammeled joy in what's otherwise quite a wearing few days.
One of my favourite things: I'm in a small but perfectly formed reply-all-pocolypse in work. Just 170 people, but so far ~35 increasingly irate replies telling everyone else to stop replying, ~10 demanding to be unsubscribed, and 1 hero who replied-all with "I'm just here for the drama 🍿".
There's something incredible about the thought process "the previous thirty people all telling each other to stop are the problem, but *my* reply-all telling people to stop is the solution we need". Amazing.