I said I clean up chats weekly, but honestly, I also delete small or casual ones right after they’re done.
So the “weekly cleanup” takes maybe a minute total.
I think whether to keep chats depends on your goal. I use AI mainly as a tool for work or quick problem-solving, so I don’t need to preserve long conversations.
But if someone uses AI more like a friendly companion, I totally get why they’d want to keep the history.
When I get a really good answer, I save that text elsewhere and still delete the chat.
That’s why my ChatGPT sidebar rarely has more than about 20 chats.
I just clean up old chats every week.
I keep maybe 3–5 that matter.
If I need the info again, I’ll just ask ChatGPT — faster than digging through history.
I think this piece makes a strong point — when there’s already a working model, just copy it instead of endlessly debating. The homelessness crisis is real, and doing nothing while watching it grow worse is the worst option. Of course there’s a chance it fails, but the bigger issue is that no one wants to take responsibility if it does. That lack of strong leadership is, in itself, part of the problem.
This is really impressive! With Canada’s housing prices skyrocketing, this dataset seems incredibly useful. I’m not in this field myself, so I can’t directly make use of it, but it definitely looks like it has a lot of potential. That said, given the massive scale, I can’t help but wonder how sustainable the maintenance will be.
I think in a similar way, though from a slightly different angle. For me, the value of stopping on time isn’t just about avoiding overtime — it’s also about not waiting for a clean break.
When I wrap things up too neatly, the next day feels like a cold start, and that makes it harder to dash into new work. But if I deliberately leave a task half-finished, then the next day I can just pick up where I left off and get moving much faster.
Totally feel this. I once found an entire site built with nothing but MySQL timestamp. I switched everything over to DATETIME, but since I did it in a straightforward way, I kept worrying there were hidden bugs lurking. In the end I just closed the laptop and thought, “whatever happens, happens.”
I think the article nails it. AI makes spinning up code almost too easy, but then you get services where ops or security were barely considered. That’s also why people with those skills are still in demand — they’re the ones holding things together for now. It won’t last forever, AI will eventually move into those areas too, but until then it’s still on humans to deal with it.
Interesting point! I hadn’t really thought about it in terms of surveillance. For me the appeal was more about comfort and safety — things like detecting gas leaks, fires, or other hazardous smells. In that context, I wouldn’t feel any downside. But yes, how it’s used will matter a lot.
I think whether to keep chats depends on your goal. I use AI mainly as a tool for work or quick problem-solving, so I don’t need to preserve long conversations. But if someone uses AI more like a friendly companion, I totally get why they’d want to keep the history.
When I get a really good answer, I save that text elsewhere and still delete the chat. That’s why my ChatGPT sidebar rarely has more than about 20 chats.