Only the opening sentence has an AI smell; the rest is definitely written by a fleshy meatbag

I have a December 2024 XPS 15 and I regularly get 7-8 hours out of a charge whilst doing a mixture of tasks. On Linux too, no less.

At least now I'll be able to view all those broken Imgur links here in the UK.

Yes this is my use-case for it too - it's great to generate a structure which I will keep but I always end up reworking all the actual content so it sounds like me. It is a great way to get past the 'getting started' hurdle though.

This is a you thing. I had the same pair of Sony wireless headphones for years and I only replaced them because the ear cups started disintegrating. Their replacements (also Sony) have already lasted me a couple of years with no issues. I also have absolutely no problems with Bluetooth either, the headphones are paired with maybe 6 devices across iOS and Linux and they never fail to connect.

I (and I'd wager most other meatsacks here) use HN to engage with real people with real opinions. Not with robots.

I believe like that was the intent, but the (very few) mentions of Jira feel like a bit of a non sequitur; they don't belong.

I sandbox everything inside https://github.com/strongdm/leash

That way the blast radius is vastly reduced.

This is why I won't run Claude without additional sandboxing. I'm currently using (and quite pleased with) https://github.com/strongdm/leash

Why? The AI is just regurgitating tokens (including the sycophancy). Don't anthropomorphise it.

Because I was only 55% sure my comment was correct and the AI made it sound like it was the revelation of the century

Because of the way regurgitation works. "You're absolutely right" primes the next tokens to treat whatever preceded that as gospel truth, leaving no room for critical approaches.