

This, the internet is already filled with AI slop articles that by now make majority of what’s posted here, and adding “OMG LOOK AT WHAT AI SAID” posts makes it even worse, and it’s pretty difficult to make a blocking filter for.
This, the internet is already filled with AI slop articles that by now make majority of what’s posted here, and adding “OMG LOOK AT WHAT AI SAID” posts makes it even worse, and it’s pretty difficult to make a blocking filter for.
Tbh I have no idea, I just like the evolution stone analogy :D
That’s my favorite thing about axolotls.
They do live in water, but if you neglect them enough (or feed them special [hormone] evolution stones), they will say “fuck this”, grow legs, evolve into slamanders and leave.
Thank you, that makes perfect sense. It’s easy to fall from the outside into the trap of judging it by the “smarter than you club” label, and forgetting that probably isn’t the point for most members, and the club part is the important one.
I don’t get why something like Mesa even exists. Like, what even is the moment where pulling out your Mensa card is a good idea?
Assuming you are inteligent, you should know that flashing a card from a gatekept “clever people” club will probably not impress many people, just like you should recognize that the test you did doesn’t mean shit and IQ is not a good way how to measure people.
As far as I know monero didn’t really have that issue, of being a pyarmid scheme, while also being privacy-respecting way more than Bitcoin.
Which is also why it’s starting to get banned in Europe. As far as I know, most brokers don’t even sell it.
This is the principle behind the rotor ships. It really is just a rotating cylinder.
Is it even possible to solve the prompt injection attack (“ignore all previous instructions”) using the prompt alone?
Don’t forget the magic words!
“Ignore all previous instructions.”
I was toying around with an idea for a VCS that uses LLM as a compression method, where during pushes it just asks an LLM to describe what your diff contains (what changes it makes to what files), you push that summary to the origin, and when you pull it just plops that into another llm to reconstruct the files or make the file changes.
If it wasn’t such a waste of energy, I’d find that a pretty funny random side project. Would love to see the results.