This definition of social media is new to me as well, thanks for sharing it. This sort of clarifies a term I really dislike, and which you've used: "the algorithm". It's always seemed a little murky to me which algorithms it refers to. It's like saying "don't eat food with chemicals in it".

Lemmy does have "an algorithm", it's just a relatively simple one based on communities one is subscribed to plus some vote/comment data for the various sort orderings.

Lemmy also absolutely implements a social graph -- the data about who has interacted with whom is all stored by the system. It's not explicitly stored as a graph structure, but then we're arguing database schemas.

As I understand it, however, you're saying "social media" arises when the "social graph" data structure is used as an input to "the algorithm". That seems like a pretty robust definition to me.

One bit of pedantry: user blocks on Lemmy are, by a general definition, a form of social graph, and they do affect what content people see. So Lemmy could technically qualify as social media by the definition I've written here. I'm not sure what a more precise definition could be that avoids this technicality.

This was an interesting read, but it's only discussing blue light filters as they affect melatonin and thus sleep cycle. It doesn't say anything about other reasons to use them, which for me are:

• Blue LED light is linked to long term macular degeneration, it may also have negative effects on the retina in the shorter term.^[https://en.wikipedia.org/wiki/Biological_effects_of_high-energy_visible_light#Blue_LED_light_hazard] It's not completely clear to me whether these effects would also be basically unhindered by a blue light filter, as the article describes; it gives me no reason to think they would but I'm not a neuroscientist.
• When I'm already using a dark theme with my screen at minimal brightness (as suggested by the article), using a filter lowers the total luminance even further (as suggested by the article).
• It feels less straining on my eyes; maybe that's purely psychological but hey I'll take it.
• It's cozy :3

Given this the article title seems sliiiightly grandiose, but perhaps most people are really only in it for the melatonin thing.

I'm surprised how many people seem offended by this comic. I found it pretty relatable. That doesn't mean I "don't understand context", or think the writers were bad people, or that the shows aren't worth watching. It just means I find it personally unpleasant to find these jokes in a work I'm otherwise enjoying.

When kids study older literature and media in school, generally when there's a slur or racist reference or joke, the teacher will stop and explain the context and get the kids to reflect on it and why it's probably not acceptable today. Even though I understand this and know it going in, I'm still kind of doing an abridged version of that in my head when something like this comes up in a show -- I've been following along, laughing with the writers, and then suddenly I'm backing up and distancing myself from one joke or idea. It's jarring, it pulls me out of the show, and it's just not fun.

In some cases it also comes across as incredibly lazy and unoriginal. So many sitcoms from that era have "the trans episode", "the gay episode", "the lecherous character" -- and they all make the same unfunny jokes, and it's a reminder than a lot of these shows, even in their time, were just not that creative. Plenty of modern shows have the same problem, but they don't draw attention to it by having large classes of "stock jokes" that simply do not land today.

It's a screenshot of this report from a review of the UK's security and terrorism legislation, published in December.

TechRadar article discussing the specific encryption issue here.

I was skeptical given the grammar issues others have pointed out but it seems legitimate.

Interesting, thanks for doing the research!

As an extreme non-expert, I would say "deliberate removal of a part of a model in order to study the structure of that model" is a somewhat different concept to "intrinsic and inexorable averaging of language by LLM tools as they currently exist", but they may well involve similar mechanisms, and that may be what the OP is referencing, I don't know enough of the technical side to say.

That paper looks pretty interesting in itself; other issues aside, LLMs are really fascinating in the way they build (statistical) representations of language.

This is a good name for one of the main reasons I've never really felt a desire to have an LLM rephrase/correct/review something I've already written. It's the reason I've never used Grammarly, and turned off those infuriating "phrasing" suggestions in Microsoft Word that serve only to turn a perfectly legible sentence into the verbal equivalent of Corporate Memphis.

I'm not a writer, but lately I often deliberately edit myself less than usual, to stay as far as possible from the semantic "valley floor" along which LLM text tends to flow. It probably makes me sound a bit unhinged at times, but hey at least it's slightly interesting to read.

I do wish the article made it clear if this is an existing term (or even phenomenon) among academics, something the author is coining as of this article, or somewhere in between.

GPT-4o mini, "Rephrase the below text in a neutral tone":

This name is appropriate for one key reason: I have not felt the need to use an LLM for rephrasing, correcting, or reviewing my writing. This is also why I have not utilized Grammarly and have disabled the "phrasing" suggestions in Microsoft Word, which often transform a clear sentence into something overly corporate or generic.

Although I wouldn’t categorize myself as a writer, I have been intentionally editing myself less than usual lately to avoid the typical style associated with LLM-generated text. This approach might come across as unconventional at times, but it can also make for more engaging reading.

I also wish the article clarified whether this term is already established in academic circles, if the author is introducing it for the first time, or if it falls somewhere in between.

"avoid the typical style associated with LLM-generated text" -- slop!

Yeah, even though I have a bit of background I can't really make heads or tails of that OpenSearch doc at a glance, it's dense stuff.

In my experience knowing the keywords to stick in a search engine is often half the battle; there are plenty of resources out there on "vector databases". "Semantic search" from the lede of the OpenSearch doc might be another good one to have around.

Feel free to ask me any other questions and I can try to answer to the best of my abilities, though again, not an expert and honestly I've never actually used these myself beyond toy examples.

I'm not an expert, but it sounds like you want an embedding+vector database. This essentially extracts the part of an LLM that "understands" (loaded term, note the quotes) the text you put in, and then does a lookup directly on that "understanding", so it's very good at finding alternate phrasings or slightly differing questions.

There's no actual text generation involved, and no need to retrain anything when adding new questions.

OpenSearch has an implementation (which I learned about just now while writing this comment and thus cannot vouch for); you could start there.

My assumption for the key icon was something to do with PINs/passkeys, which kind of reinforces OP's point.

Ngl I really want to know what the tick icon actually does now.

And "a11y" is the most obscure -- dare I say... inaccessible -- fucking abbreviation of "accessibility". For years I only saw them in passing and assumed both these things were like, quirkily-named Javascript frameworks or niche standards documents or something, despite knowing quite well the concepts they actually refer to.

I recently started watching this, but I think I have similar feelings to you, because once it went out to the wasteland I started getting less enthused and stopped watching after a few episodes. I've been meaning to get back to it and see it through -- although it sounds like you're not particularly rosy on it, hearing there's a "game show episode" makes me think I need to at least see what that's about.

I do really like the soundtrack; New Pulse in particular has a quintessentially cyberpunk feel for me.