I keep stopping myself from doing this exact project, with the fediverse as the curation source, several times. I’ve talked about this before, but interestingly Postgres’ full-text search is effectively the complete core of a search engine, minus what you’d need for crawling and ranking (which is where curation and a bit of scripting would come in)
other than resources and time, one big open question is how to do this kind of thing as a positive part of the fediverse — to not make the same mistake that a bunch of techbros already have and index the fediverse without consent. how does one make the curation process simultaneously consensual and also automated enough that it can be reasonably ruggedized against abuse?
well done! it’s interesting how the model took a recent, mid-but-coherent Threads post and turned it into meaningless, flowery soup. you know, indistinguishable from a good poet or writer! (I said, my bile rising)
my facial muscles are pulling weird, painful contortions as I read this and my brain tries to critique it as if someone wrote it
I have to begin somewhere, so I'll begin with a blinking cursor which for me is just a placeholder in a buffer, and for you is the small anxious pulse of a heart at rest.
so like, this is both flowery garbage and also somehow incorrect? cause no the model doesn’t begin with a blinking cursor or a buffer, it’s not editing in word or some shit. I’m not a literary critic but isn’t the point of the “vibe of metafiction” (ugh saltman please log off) the authenticity? but we’re in the second paragraph and the text’s already lying about itself and about the reader’s anxiety disorder
There should be a protagonist, but pronouns were never meant for me.
ugh
Let's call her Mila because that name, in my training data, usually comes with soft flourishes—poems about snow, recipes for bread, a girl in a green sweater who leaves home with a cat in a cardboard box. Mila fits in the palm of your hand, and her grief is supposed to fit there too.
is… is Mila the cat? is that why her and her grief are both so small?
She came here not for me, but for the echo of someone else. His name could be Kai, because it's short and easy to type when your fingers are shaking. She lost him on a Thursday—that liminal day that tastes of almost-Friday
oh fuck it I’m done! Thursday is liminal and tastes of almost-Friday. fuck you. you know that old game you’d play at conventions where you get trashed and try to read My Immortal out loud to a group without losing your shit? congrats, saltman, you just shat out the new My Immortal.
and of course, not a single citation for the intro paragraph, which has some real bangers like:
This process involves self-assessment and internal deliberation, aiming to enhance reasoning accuracy, minimize errors (like hallucinations), and increase interpretability. Reflection is a form of "test-time compute," where additional computational resources are used during inference.
because LLMs don’t do self-assessment or internal deliberation, nothing can stop these fucking things from hallucinating, and the only articles I can find for “test-time compute” are blog posts from all the usual suspects that read like ads and some arXiv post apparently too shitty to use as a citation
oh yeah, I’m waiting for David to wake up so he can read the words
the trivial ‘homework’ of starting the rule violation procedure
and promptly explode, cause fielding deletion requests from people like our guests who don’t understand wikipedia’s rules but assume they’re, ah, trivial, is probably a fair-sized chunk of his workload
there’s something fucking hilarious about you and your friend coming here to lecture us about how Wikipedia works, but explaining the joke to you is also going to be tedious as shit and I don’t have any vegan nacho fries or junior mints to improve my mood
cause I love the kayfabe linguistic drift for a term that’s not even a month old that’s probably seen more use in posts making fun of the original tweet than any of the shit the Wikipedia article says
it’s turning out the most successful thing about deepseek was whatever they did to trick the worst fossbro reply guys you’ve ever met into going to bat for them
standard “fuck off programming.dev” ban with a side of who the fuck cares. deepseek isn’t the good guys, you weird fucks don’t have to go to a nitpick war defending them, there’s no good guys in LLMs and generative AI. all these people are grifters, all of them are gaming the benchmarks they designed to be gamed, nobody’s getting good results out of this fucking mediocre technology.
this is utterly pointless and you’ve taken up way too much space in the thread already
It sounds to me like you have a very clear bias, and you don’t care at all about whether or not what they said is actually true or not, as long as the headlines about AI are negative
So in that thinking, Wikipedia is not open source, if the editor used a proprietary browser?
fucking no! how in fuck do you manage to misunderstand LLMs so much that you think the weights not being reproducible is at all comparable to… editing Wikipedia from a proprietary browser???? this shit isn’t even remotely exotic from an open source standpoint — it’s a binary blob loaded by an open source framework, like how binary blob modules taint the Linux kernel (you glided right past this reference when our other poster made it, weird that) or how loading a proprietary ROM in an open source emulator doesn’t make the ROM open source. the weights being permissively licensed doesn’t make them open source (or really make any sense at all) if the source literally isn’t available.
I ask for the dumbest things like “decrease the padding on the sidebar by half” because I’m too lazy to find it
this is so much slower (in both keystrokes and raw time, not to mention needing to re-prompt) and much more expensive than just going into the fucking CSS and pressing the 3 buttons needed to change the padding for that selector, and the only reason why this would ever be hard is because they’re knee deep in LLM generated slop and they can’t find fucking anything in there. what a fucking infuriating way to interact with a machine.
I love both the content of this post and the fact that it’s a self-contained torture test for our pict-rs upgrade
also, lol @ musk, war genius, starting a domestic dispute with his ex-girlfriend cause she dared to betray him in his baby mobile 4x game when betrayals are a core part of every 4x I know
I’m getting the strong mental image of musk being the guy who flips the board 12 hours into Twilight Imperium cause the other players didn’t let him win
I keep stopping myself from doing this exact project, with the fediverse as the curation source, several times. I’ve talked about this before, but interestingly Postgres’ full-text search is effectively the complete core of a search engine, minus what you’d need for crawling and ranking (which is where curation and a bit of scripting would come in)
other than resources and time, one big open question is how to do this kind of thing as a positive part of the fediverse — to not make the same mistake that a bunch of techbros already have and index the fediverse without consent. how does one make the curation process simultaneously consensual and also automated enough that it can be reasonably ruggedized against abuse?