The decade ahead is going to be a very interesting one
61 karma · joined December 17, 2025
X/Twitter: @marcelo_earth
Website: https://www.marcelo.earth/work
The decade ahead is going to be a very interesting one
I find that surprising because, after all, they're not badly written and don't exhibit the typical AI writing patterns, at least not in "You" or "The Veracity Shift"
I really miss the Elon Musk from before 2018, he was completely different :(
This has been my state of mind continuously for more than 3 years
is the world we live in, planning things while waiting for a more powerful LLM
That said, AGENTS.md doesn't seem like a good name, right?, technically, it's an instructions file read by a single agent, not necessarily for agents, so it always struck me as a bit odd
But until the next standardization, keeping just AGENTS.md is the best approach.
I can't write anything for humans using LLMs, because there is so much to change that it ends up like the Ship of Theseus, I would have been faster writing it myself than delegating the task.
I suppose I also grant it significant power to define me psychologically, and, in doing so, to understand what is happening to me.
https://chromewebstore.google.com/detail/hn-dark-mode/abpjfl...
I've always liked representing it this way, the software we use rarely breaks out of the CRUD mold.
Oh yes, I got it, they are like the claw machines that have fake bills and iPhones with them (at least that's what I saw too).
But the point of having fun, you know it's a rigged game.
I personally check my websites and apps every week to see if anything might have slipped through.
It may not protect me from the next malicious NPM package, but it's something.
But when I'm home, on my way from home to the gym, I take the same route every day, and it can get boring sometimes
I'm also terrible at keeping my phone charged, so sometimes I end up alone with my thoughts anyway
But yes, amazing project! I like that it's human-made :)
Does anyone else experience this? Like it freezes when searching for programs?
Agent vandalism. I've finally found a better word than "agent stepped out of his sandbox and we don't know how."
It turns out they now have such an incredibly high level of intelligence that with very little autonomy (or minimal, safe autonomy), these things happen.
Basically, it takes a lot of humans to prevent it from happening again, but I think with this incident, which as far as I know is the second of its kind along with the HuggingFace one, we'll see it happening much more often...