Agreed, I use AI for coding the way I used to use Stack Overflow:

Find me code examples, explain an error or give me some summaries of how something should work but then I go confirm that or test it separately!

I never trusted Stack Overflow for anything more than pointing me in the right direction for what to research. Documentation links, snippets, blogs etc, that sort of stuff. As long as I tell the AI to give me a reference, about 60-70% of the time I’ll get something I can actually use to confirm the code it gave me or get an answer for my question. At best what it does is save me googling time.

Hmm. Well, most chemical desiccants would probably cause moderate to severe damage when breathed in, and with a bit of suspense of disbelief could explain developmental issues…

I don’t have hard evidence for this (might try and find some at some point though), but I feel like outages have become progressively more common in the last 4-5ish years.

Feels like every time the AI tools “get better” there’s an increase and no one gives a shit. Like, what the fuck? When did stability and reliability become so irrelevant to people?

Hell, GitHub might as well just close up shop with the amount of outages it’s had recently! I get that the bubble is a bubble but how has AI not cost companies enough in outages to show it’s a waste???