Terracotta
18d ago
So effectively you're using ChatGPT as... an ad blocker for spammy sites?
That's a pretty interesting development in the eternal war of consumer versus enshittification. It'll become still more so when all the wiki content is itself LLM-authored and the LLMs pivot to putting secret ad space in their system prompts, like Google's sponsored results.
Terracotta
18d ago
It still leaves unanswered questions, though, because however cursed bars and the internet may be, it's not like they actively interfere with developing relationships by more normal means (do they?).
Nobody needs another rape-culture/ perving-at-work debate, so let's set aside the decline in school and workplace relationships, but that chart also shows an approximately 35% drop in the proportion of people who met through friends and a 50% drop in the proportion who met through family. Say in 1995, Ann's cousin might have set her up with his cute pre-vetted army buddy Jim, or Cathy might have invited her friend Dave to a board game night with one of the single girls from her softball league. Well, cousins, army buddies, softball leagues, personally compatible humans still exist, so what's happening to interfere with those connections now? Do Ann and the army buddy still meet, but now he thinks she's too fat or she thinks he's too short compared with the hotties they shop online? Do Dave and the softball friend still do board games, but now they're under-socialized and both kind of self-absorbed, so neither of them makes a move while still feeling offended at the other sex's lack of interest? Or what?
Terracotta
18d ago
And maybe it's regional, but after HS I never once encountered a woman who wasn't "acting like that".
This feels so bizarrely foreign, because almost every married couple I know, myself included, built their early relationship in a way that closely matches @urquan's account. This happened mostly in college, but with a smattering of post-college relationships as well. Just a lot of average-looking, average-quality people hanging out and doing random social club things, shyly getting to know a similarly average-looking person and asking them to a play or movie or something, eventually getting serious then either breaking up or getting married and starting a family in a more-or-less dual-career household. Nobody "acted like that," that I'm aware of. No first-date hookups, negging, harems, nude pic demands, findom, tradwifery, false or true rape accusations. Very rarely any cheating, even. The guys were mostly respectful, earnest and nice, the women were mostly honest and friendly. Some of those marriages got worse over time, but many are still doing OK.
I would really love to know where all these apparently horrible young singles (of both sexes) come from. Are people trying to date way above their league and getting toyed with as a result? Did all the helicopter parenting just raise a generation of unpleasant narcissists who will never play well with others?
Terracotta
18d ago
It’s more akin to web surfing or browsing Wikipedia than chatting on a forum or whatever. I will use it as an open format encyclopedia and explicitly not as a conversationalist sounding board.
OK, this has mystified me for a long time. I use LLMs for various editing, writing, coding tasks, occasionally to kludge a moderator for party games, to simulate human feedback on human-oriented questions, and once in a long while to suggest a starting point for a lit review or to locate a half-remembered link. But can you help me understand the "encyclopedia" and "web surfing replacement" use-cases, when we have actual encyclopedias and a web to surf?
When I see a granny or a teen just asking ChatGPT, I assume it's because they can't internet, can't read, or don't give a shit about the quality and provenance of their information, but for a super-online, epistemically hyper-aware Mottizen to do this feels like hearing someone say they hire a guy to order all their food, chew it and spit it in their mouth.
Yeah, I do understand using the LLM for search or even for a link-enriched overview to cross-check with real resources, as you describe.
I mostly get confused when people Ask ChatGPT, consume the generated content and stop there, which (for a Motte level of understanding "assertions can be wrong," "sources can be mistaken," "context matters," "models sometimes confidently hallucinate") seems like a weird combination of definitely caring and definitely not caring about whatever fact you're researching.
More options
Context Copy link