Isn't the benefit from LLM that anyone can create that little software that does scratch the particular needs the user has. Once scratched it's done its job. Rinse and repeat the next time. There is no longer the need to clean and maintain code for the next time. A bit like fast fashion! We are doomed.
This can be due to missing address information in OSM. I also find the grouping sometimes odd, e.g. searching for a street, the place names are from one level higher.
True, but how come such risks are addressable when adding AI or opening up to yet another API or when some savings are promised with a new product/product feature?
I'd say it is. Yes there are people that own guns or hunting rifles. Most still don't think about guns or shooting first. Guns are supposed to be locked in a safe etc.
All that does obviously not apply to a criminal who does not follow the law.
I'm with you on not liking shorts. I read there is a new option to limit time spent in shorts, if you set that to 0 they do go away. Have not tested it.
Honest question, I wonder why that is? Surely we have smart humans that did not read and learn "all the books". Can AI not be trained by re-reading material multiple times to reinforce?