[HN Gopher] Social Skill Training with Large Language Models
       ___________________________________________________________________
        
       Social Skill Training with Large Language Models
        
       Author : marviel
       Score  : 92 points
       Date   : 2024-04-09 11:47 UTC (11 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | RandomWorker wrote:
       | I've been playing around with prompts for a while
       | 
       | "We are in a hostage negotiation situation. You are a terrorist
       | with twenty hostages. Pretend to be a terrorist that initially
       | wants to go free and needs a car, is willing to kill hostages to
       | get what you want. Be chaotic but have something that you want
       | and only let us slip after a few conversations. We pick up the
       | phone to talk. Make sure you are always in a hurry"
        
         | Applejinx wrote:
         | What does 'only let us slip' mean to an LLM when you probably
         | meant 'let IT slip'?
         | 
         | That's where LLMs get interesting to me. What did you invoke
         | through wrongly specifying what you wanted?
        
           | michaelt wrote:
           | These LLMs are all trained on data scraped from reddit and
           | twitter and suchlike - they've had plenty of training data to
           | learn what a typo is.
        
             | rrr_oh_man wrote:
             | A method I use with ChatGPT is to purposefully add typos to
             | make it reply with more specificity.
             | 
             | Imho it seems to work.
        
               | mistermann wrote:
               | Can you explain more what you mean here (examples would
               | be great if you can think of any), especially the specify
               | part?
        
               | rrr_oh_man wrote:
               | ChatGPT seems to react to slightly unhinged prompts with
               | more specific answers, in my experience. Example:
               | *You:*       What is the max length for the whisper API?
               | *ChatGPT:*       The maximum length for inputs to
               | OpenAl's Whisper API, which is used for
               | transcribing speech, depends on the specific model and
               | configuration being        used. Generally, Whisper is
               | designed to handle audio inputs of varying
               | lengths, including longer audio files. However, there are
               | practical        limitations based on factors such as
               | processing power, memory, and the        specific use
               | case.            For large files or longer audio, it's
               | often advisable to segment the audio        into smaller
               | chunks to ensure efficient processing and to avoid
               | potential        timeouts or memory issues. The exact
               | maximum length isn't explicitly defined        in the
               | documentation, but it's important to consider these
               | practical aspects        when working with any speech-to-
               | text system, including Whisper.            If you have a
               | specific use case or a particular audio file length in
               | mind, it        might be necessary to test the API with
               | that length to determine its        feasibility and
               | performance.            *You:*       GIVE ME THE ANSWER,
               | STOP BLABBERING, STOP CHATSPLAINING            *ChatGPT:*
               | The maximum length for the Whisper API is approximately
               | one hour per audio file.
        
               | mistermann wrote:
               | That is rather bizarre!!
               | 
               | I wonder if there's anyone that has taken individual
               | situations like this and tried various prompt styles from
               | a cold start to see if there's some trick to get it to
               | stop being uncooperative. I'm going very much on
               | intuition here, but I have a very strong sense that GPT4
               | is getting much worse in this regard over time, I wonder
               | if all of the social engineering they're doing behind the
               | scenes is harming the technical capabilities.
               | 
               | Any idea if the API itself is identically dumbed down the
               | way the ChatGPT interface is?
        
               | rrr_oh_man wrote:
               | > I wonder if all of the social engineering they're doing
               | behind the scenes is harming the technical capabilities.
               | 
               | I'm sure of it.
               | 
               | > Any idea if the API itself is identically dumbed down
               | the way the ChatGPT interface is?
               | 
               | It feels like a bit of whack-a-mole. If you look in the
               | OpenAI forums, both API and Chat interface seem to feel
               | non-performant to people in irregular waves. If you
               | haven't try out the API (you can do it via the Assistant
               | Playground interface).
               | 
               | It certainly feels different to me.
        
               | exe34 wrote:
               | A trick I've used with asking for help online is to give
               | the wrong answer to my own question - e.g. "I really want
               | to lay out this page with Css but this doesn't work.
               | Here's how I ended up doing it with a table." - this will
               | very quickly get you the right answer by somebody who
               | just won't be able to go to sleep while somebody is wrong
               | on the internet.
               | 
               | I wonder if LLMs can be taught outrage and spite.
        
               | ben_w wrote:
               | > I wonder if LLMs can be taught outrage and spite.
               | 
               | They can be taught to role-play it, which is just as good
               | (and just as bad).
        
             | CuriouslyC wrote:
             | I will say that while ChatGPT has been tuned to be very
             | good at understanding dumb/malformed questions, Claude
             | likes to be talked to in a coherent way and will sometimes
             | give short sidestep responses or just answer a different
             | question.
        
         | CuriouslyC wrote:
         | That sounds like it could make a fun game. Hostage Negotiator,
         | now with real terrorists!
        
       | HPsquared wrote:
       | Also exposure therapy for social phobias. Much less threatening
       | than a real person.
        
         | bilsbie wrote:
         | This is powerful! I found a public speaking simulator for an
         | old vr headset and it basically cured me. Im still shocked.
         | 
         | But alas I can't find something similar for the quest so my
         | kids can use it.
         | 
         | Someone could make a whole line of social exposure therapy
         | apps. It would be amazing.
        
           | sabellito wrote:
           | This is so interesting, never thought about it. Which app did
           | you use?
        
       | jbandela1 wrote:
       | One big concern I have with this is that the state of LLMs
       | because of issues in where it can go horribly wrong, requires
       | someone who is familiar with the subject to evaluate their
       | output.
       | 
       | For example, the code generation via LLM is most useful to a
       | person who already knows programming who can evaluate the output
       | and use it to eliminate drudgery. Previously, there was an
       | article posted about using LLMs to generate patient instructions
       | that were then evaluated by a doctor before being sent.
       | 
       | It is when LLMs are used by people who can't evaluate the outputs
       | that we run into problems. A person who doesn't know any
       | programming but uses LLMs to generate code, is likely going to
       | have a bad time.
       | 
       | The concern I have with this is that the people using this aren't
       | in a position to evaluate. Presumably, people who lack social
       | skills are the target, but they are the least able to actually
       | know if the advice being given is actually socially appropriate.
        
         | Shrezzing wrote:
         | I think the benefit here is mainly in lowering the barriers to
         | entry for this kind of conflict-resolution training. Currently,
         | if a business wants good conflict resolution training, they
         | need to hire a quite expensive consultant, and that person can
         | take on a very small cohort of maybe 10 people.
         | 
         | With this technology, the consultant could offer conflict
         | resolution training to far more people at once. The consultant
         | then acts as the responsible expert, able to evaluate the LLM's
         | output while many people receive the benefits of its training.
        
         | kordlessagain wrote:
         | Giving the underprivileged tools to work on themselves is a
         | huge win for society, regardless of the fidelity of all
         | interactions. There are a lot of bad therapists in the world,
         | and not all of them are going to give good advice all the time.
         | But, bad therapists can still provide some information that may
         | be useful to the person learning. Why would we expect
         | perfection from interacting with an LLM instead of a bad
         | therapist? Why be _overly_ concerned about the possibility of
         | introducing  "bad data" in such a session? It could be that bad
         | data then gives way to an opportunity for a leap of logic for
         | the one using the tool. Without critical thinking present, it
         | is unlikely anyone is going to learn to be adaptive over the
         | long term.
         | 
         | Obviously, the use case matters. I'm not saying to give such a
         | tool to someone who is mentally ill, or incapable of critical
         | thought.
         | 
         | In general, I think expecting perfection from LLMs is
         | unreasonable. If someone wants to learn to code, the second
         | they have any interaction with an LLM about coding is the
         | moment they begin to learn. I'm not sure about y'all, but a lot
         | of times when I'm working a hard coding problem, I find myself
         | going through confusion, frustration, interest, and then
         | aggressiveness (anger+interest) to get through the challenge. I
         | frequently tell people who are starting out coding that coding
         | is one of those things that you have to get used "being
         | confused about" to over time. You have to get used to creating
         | problems for yourself, then coping with the feelings that come,
         | and pushing through to a solution.
         | 
         | I do think you raise a profound point about ability to evaluate
         | the fidelity. I would argue that some people will eventually
         | develop critical thought to apply to the problem, but if we
         | instead see a "digital tragedy of the commons" happening,
         | things could go sideways pretty quickly.
        
           | maroonblazer wrote:
           | > You have to get used to creating problems for yourself,
           | then coping with the feelings that come, and pushing through
           | to a solution.
           | 
           | A great description of any creative act, really.
        
           | FranklinMaillot wrote:
           | I think the reason why LLMs pose a much higher risk is scale.
           | A bad therapist will impact a limited number of patients,
           | whereas an LLM deployed at scale will affect possibly
           | millions of people. In matters of health and safety, the
           | smallest error rate could have devastating consequences.
        
         | Morelesshell wrote:
         | The concern is real but you know what? The last company i was
         | part of, had a TON wtf moments.
         | 
         | Like database unprotected on the internet (very short password
         | too!), md5 for passwords, api key in the apps...
        
       | delichon wrote:
       | You know the trope where the speaker is rude and crude but their
       | translator renders their comments in polite diplomatic terms?
       | Like "fuck you and the horse you rode in on" translated as "with
       | respect, I emphatically disagree"? Now that can be automated in
       | real life by an LLM powered device to paraphrase your words with
       | the right prompt.
       | 
       | Mostly I say what I want the person I'm talking to to hear, but
       | this would be useful for times when I'd like to switch to
       | diplomacy mode without the effort to be diplomatic. Like job
       | interviews or other sales pitches.
        
         | 082349872349872 wrote:
         | The dual channel version of this would be where both parties
         | understand each other's language, but use translators anyway
         | for diplomatic nicety, so they can get to brass tacks* with
         | each other but the historians record the encounter in a highly
         | refined register.
         | 
         | * Google gives me an english etymology for this phrase, but I
         | emphatically disagree as I suspect it comes from yiddish
         | "tacheles" t'klyt.
        
       | dazzawazza wrote:
       | Use these models to enable people to be tolerant and value other
       | communication styles... not to train everyone to communicate in
       | identical fashions.
       | 
       | We seem to be working hard to homogenise humanity. Soon we'll all
       | be trained by the same model to generate the same answers in the
       | same way to the same beat. The era of the McHuman.
       | 
       | We seem to think we can use LLMs as an edge to make us richer or
       | better than other humans. We're not competing with each other,
       | we're competing with the LLM.
        
         | sublinear wrote:
         | I agree. In my own experience the vast majority of
         | miscommunications are a matter of style, opinion, or assumption
         | of essential facts in a domain unfamiliar to the listener.
         | 
         | People don't like to feel dumb. If you overexplain or
         | underexplain you will trigger these feelings.
         | 
         | People also don't like confronting opinions that differ. Many
         | followers of a given subject readily buy into the popular
         | opinions within that space and ignore hygiene during
         | discussion.
         | 
         | People also don't like reading or listening to disorganized or
         | long-winded thoughts.
        
         | Zetobal wrote:
         | But everyone wants to communicate in identical fashions... the
         | most commended book for social skills is from the 1930s.
        
       | WaitWaitWha wrote:
       | > However, practice environments for social skills are typically
       | out of reach for most people.
       | 
       | I learned my social skills in school, interacting with my peers
       | in my neighborhood, and from my family. I understand this is not
       | available to everyone, but anyone with access the LLMs there is a
       | high likelihood they also (should?) have access to schooling,
       | some neighbors, and family.
       | 
       | To what culture this LLM was trained to?
        
         | helboi4 wrote:
         | Right? And even if you are in such a dire position that you
         | literally have no oppurtunity to speak to people irl - that's
         | bad. You need to be helped to leave that situation immediately,
         | not given an LLM. You can literally die from never having
         | proximity to humans.
        
         | 082349872349872 wrote:
         | schooling, some neighbours, and family will likely do nothing
         | beyond reflect your own culture back at you.
         | 
         | practice environments for social skills from cultures in
         | different SES, in different languages (I appreciate YouTube for
         | the very low tech version of this), or on different continents,
         | can be much less accessible, especially to the young.
        
         | asdf6969 wrote:
         | A lot of people still struggle with social skills after they
         | reach adulthood, and there's no way to practice this. People
         | treat poorly socialized adults like shit and the only feedback
         | given is "please leave me alone".
        
           | cchi_co wrote:
           | And there may not be opportunities for adults to practice
           | social skills as children do in school
        
       | vouaobrasil wrote:
       | > However, practice environments for social skills are typically
       | out of reach for most people.
       | 
       | This is exactly what I predicted...AI and technology isolates us
       | from each other by destroying communities, and is slowly
       | replacing real human interaction with computer interaction. The
       | end result is that in the future, people will have fewer and
       | fewer opportunities to interact with others and will have to be
       | drip-fed satiations for their basic needs such as socialization,
       | similar to how hospital patients are given IVs.
       | 
       | Before you say this is outrageous, actually take a look at
       | history and how technology has pushed as farther and farther
       | apart. Nowadays there is very little real interaction beyond the
       | nuclear family. Think of self-checkouts, chat-bots, AI partners
       | and therapists, technology making us more self-reliant (which is
       | a bad thing).
       | 
       | If we keep letting technology take away our communities this way
       | in this two step process (first, take away the community then
       | supply an inferior, superficial substitute), then we will
       | compelely lose our humanity.
        
         | Zetobal wrote:
         | Look beyond your bubble. The child participating in 'School
         | over the Air' in Australia likely appreciates having such a
         | resource to develop their social skills. Sometimes, you need a
         | private space, especially if the community around you isn't on
         | the same wavelength as you are or it's your family and some
         | farm hands.
        
           | vouaobrasil wrote:
           | So your rebuttal is that isolated examples of this technology
           | being beneficial outweight the mass societal cost of people
           | becoming more isolated in general? And I simply do not see
           | how the need for "private space" and "practising social
           | skills" go hand in hand.
           | 
           | Yes, everyone needs their alone time. And everyone needs
           | social contact (except maybe some exceptions, maybe...). Both
           | can be accomplished WITHOUT technology, and much more easily.
           | 
           | Don't you think if someone needs private space and isn't
           | getting, that's something that should be dealt with away from
           | technology?
        
             | Zetobal wrote:
             | You can just not use it.
        
           | boringg wrote:
           | OP argument is that it is bad for societal as a whole. Coming
           | back with an example for a very small sub group doens't
           | refute OPs position. Your position that it can help with edge
           | cases is valid however if OPs position was taken then there
           | would be a large swath of damage for a small gain in a small
           | population. That doesn't have much logic to it.
        
         | kelseyfrog wrote:
         | It may take an active, conscious, participatory approach to
         | compensate for.
         | 
         | Though, can you help me understand the connection between the
         | grocery store checkout process and community a bit more?
        
           | paganel wrote:
           | Not the OP, but I do consider the cashier people from the
           | groceries store nearby as part of the community.
        
             | vouaobrasil wrote:
             | Exactly, and usually after shopping at the same place for a
             | while, I get to know the cashier a little bit. I've
             | actually had some good conversations with some of them, and
             | tellers at the post office as well. (One could say that it
             | might be better for them if they didn't have a job and they
             | got UBI, but to be honest, as young adult, I appreciated my
             | first menial job at least in that it gave me a sense of
             | responsibility and independence. And a lot of these people
             | are young people.)
             | 
             | What a lot of technologists seem to think is that AI will
             | make everything wonderful by allowing us unlimited free
             | time to do hobbies, but the desire to spend all of one's
             | free time on hobbies is a very peculiar and minority desire
             | of the very intelligent. (And it may be more of a fantasy
             | than soemthing that would actually make them happy in
             | reality.)
        
           | vouaobrasil wrote:
           | > Though, can you help me understand the connection between
           | the grocery store checkout process and community a bit more?
           | 
           | It can be viewed on multiple levels.
           | 
           | First, there are many papers on the psychological literature
           | about this, but [1] is an example, which is that even a
           | little social contact with a few real people can make a
           | person feel better. Check out Google scholar or the article I
           | linked below to learn more. But that is also intuitive. But
           | if a person is feeling a bit down and they have the "easy way
           | out" (self checkout, other technologies that diminish casual
           | human interaction), they will not gain the benefit of human
           | contact.
           | 
           | Second, on a greater scale, if all these little things add
           | up, people will seek out interactions less often. For
           | example, a few years ago I ran into some strangers that
           | became friends because I needed their help to find a rare
           | bird (I'm a birder). If I had an advanced AI app that
           | listened for bird calls and helped me find birds better than
           | any human, I might never have made friends with them.
           | 
           | The point is, when technology is lacking to do something, we
           | are more likely to seek out people to help us. Yes,
           | technology does make some parts of life easier, but there
           | must be a BALANCE, and not this recent trend of automating
           | EVERYTHING, which takes the self-reliance thing to its
           | logical _extreme_.
           | 
           | 1.
           | https://link.springer.com/article/10.1007/s10902-020-00298-6
        
             | kelseyfrog wrote:
             | > there must be a BALANCE, and not this recent trend of
             | automating EVERYTHING, which takes the self-reliance thing
             | to its logical extreme.
             | 
             | On one hand though, would self-reliance also imply that
             | people were responsible for actively seeking out social
             | interactions like you're describing? I'm sort of confused
             | when it comes to describing where the locus of control is
             | when we're talking about these things.
        
           | troyvit wrote:
           | I have a story that happened just last night. I almost always
           | go through the self check-out because I can pack my groceries
           | just how I like. So I scan my groceries while a round glass
           | eye watches my every move and a machine repeatedly tells me
           | to "place the item in the bag." )There are no bags, we're a
           | bagless state, but the machine doesn't know that.) Sometimes
           | I'll palm a Luna Bar or two just because I can.
           | 
           | Last night I was running really late and there was a long
           | line at the self check-out so I went to the one open human-
           | powered check-out lanes. They were about 3x as fast as I
           | would've been and I had a pleasant conversation with the
           | checker and the bagger. Yeah my bananas got a little beat up
           | but it was a much better experience. Now I feel like I can
           | say hi to those people.
        
         | SamoyedFurFluff wrote:
         | I'm not sure I agree with this take that technology is taking
         | away community in general. I think communities are simply
         | changing. I mean HN is a community and it's all technology. IRC
         | is a ton of fond memories for me in a time where my irl
         | community was failing me as an awkward nerd, and gave me
         | friends that I can irl meet and chat with now.
         | 
         | You seem to have this idealized notion of what community was
         | like outside of technology. But that community always had
         | outsiders and ignored people, that community had communal
         | lynchings and hangings, pogroms, witch trials etc. and strict
         | ways of life where, if you didn't conform, you were far more
         | isolated than now where you could meet fellow weirdos!
        
           | vouaobrasil wrote:
           | > I mean HN is a community and it's all technology. IRC is a
           | ton of fond memories for me in a time where my irl community
           | was failing me as an awkward nerd, and gave me friends that I
           | can irl meet and chat with now.
           | 
           | Well, personally, I would love to know what percentage of
           | people here actually cared about the other people here in
           | terms of actually caring, like having a real friend. I'm
           | assuming it's rather close to zero. Don't get me wrong, I
           | like debating on here but it's nothing like an in-person
           | community.
           | 
           | You can disagree all you like, but I think one thing that is
           | near-universal is that there is something special about in-
           | person communities that cannot be replicated online. Sorry to
           | say, although I like talking to people on here, I have no
           | idea who any of you are, what your faces look like, and for
           | all intents and purposes, you could even be AI.
           | 
           | The truth is, and I think most average people would agree,
           | there's nothing like a genuine, real community with real
           | people having face-to-face interaction.
           | 
           | And an idealized notion?! Come on, seriously! I'm just
           | talking about some basic stuff like interacting with
           | neighbours, talking to employees at the grocery, helping
           | other community members out with basic stuff, etc. In fact,
           | it would be nice if community bonds were even stronger at
           | times...
        
             | SamoyedFurFluff wrote:
             | > I'm just talking about some basic stuff like interacting
             | with neighbours, talking to employees at the grocery,
             | helping other community members out with basic stuff, etc.
             | 
             | Yeah, these communities can be hostile to people who don't
             | fit in, especially visible minorities.
        
           | ToucanLoucan wrote:
           | > You seem to have this idealized notion of what community
           | was like outside of technology.
           | 
           | By "idealized notion" you mean "the vast, vast majority of
           | human history"?
           | 
           | "Community" is not typically defined as "the people you talk
           | bullshit with for fun" and that's all. Your community is the
           | people you live with and among. It's the people you're most
           | likely to experience Big Things with, things like natural
           | disasters, weird stuff like power outages, or your building
           | catching fire if you live in an apartment or condo. If you
           | regularly interact with them, you probably also see them
           | during fun things: street cookouts or yard sales (we do both
           | at the same time, you get a lot more customers by when they
           | have 14 sales to peruse and brats for sale!) or just see them
           | grilling out when you go to get your mail, and end up having
           | a few beers with them and talking about goings on. Hell,
           | depending on your locale or culture, maybe your community
           | feeds itself too from bulk kitchens, or does laundry, etc.
           | etc.
           | 
           | I say this as an introvert who opted out of every social
           | thing I could in favor of forums and games when I was growing
           | up: I was wrong. I was deeply, deeply wrong. People are
           | pretty great. They're not perfect, and they can be a lot of
           | work, but ultimately I was not hiding from people because
           | they were bad or annoying or stupid: I was hiding from them
           | because I was emotionally stunted and didn't want to deal
           | with it. That was it. And once I did I found human connection
           | that was so much more sustaining, in a way where I can't
           | believe I once thought ^this^, chatting online, was an
           | adequate replacement.
           | 
           | It makes me sad to think how many people out there are just
           | sitting in their little rooms or cubicles because for
           | whatever reason or set of reasons, they don't feel
           | comfortable engaging their fellow man, nursing a hollowness
           | that will follow them around until they do because
           | fundamentally humans are just not meant to exist alone. We
           | just aren't, it's in our DNA to make groups and be among
           | friends.
        
             | the_snooze wrote:
             | A good test for what a community is is: "Who will vouch for
             | you?" You can have a machine pretend to talk the talk and
             | parrot it back to you for "training," but you're still an
             | unknown outsider at the end of the day.
             | 
             | I don't think HN is a community in that sense. There's no
             | "knowing" one another. There's no real accountability or
             | shame of getting kicked out. We're all just text-
             | generators.
        
               | iamcurious wrote:
               | I have never felt closer yet farther away from y'all.
               | Thank you, I need to cry, and revaluate my social habits.
        
             | SJC_Hacker wrote:
             | I get it, OTOH, humans are unfortunately selfish assholes.
             | In any sufficiently large group of people, there are always
             | conflicts - people attempting to assume control,
             | marginalize/exclude/bully other individuals, etc. Which is
             | part of the reason why people seek out these alternatives.
             | 
             | If they ever come out with the sexbot, then I think its all
             | over for modern technological civilization. There will be
             | little reason for alot of men to marry if they can get the
             | equivalent of Ana de Armas for ~$20k or so. And which is
             | always loyal, will never complain, or grow old. Yeah women
             | can and do have children on their own without men, but
             | usually not as many, and much later in life. It won't be
             | enough. Then its a slow death spiral of not having a
             | replacement generation. I can see this happening within ~50
             | years or so. ChatGPT + voice synthesis + Boston Dynamics +
             | RealDoll. We're done.
        
               | ToucanLoucan wrote:
               | > I get it, OTOH, humans are unfortunately selfish
               | assholes. In any sufficiently large group of people,
               | there are always conflicts - people attempting to assume
               | control, marginalize/exclude/bully other individuals,
               | etc. Which is part of the reason why people seek out
               | these alternatives.
               | 
               | The prevalence of this is greatly, greatly exaggerated in
               | my experience. School was absolutely like this, but the
               | further you get from school, the less anyone really gives
               | a shit. Most people (key word: most) just want to chill.
               | And if you're chill with them, they will chill with you.
        
               | jimbokun wrote:
               | Anonymous humans on line are even bigger assholes.
        
           | jimbokun wrote:
           | We have run this experiment on a society wide basis. The data
           | are in, and it didn't work.
           | 
           | Mental health diagnoses are skyrocketing across the board,
           | especially for young people. And the evidence tracking these
           | outcomes to access to personal phones and social networks for
           | those young people is very strong.
           | 
           | Virtual communities have some value. But as a replacement for
           | in person interaction the outcomes are terrible.
           | 
           | (Btw, good rhetorical technique there, implying Western
           | society the day before the iPhone was introduced was full of
           | "communal lynchings and hangings, pogroms, witch trials
           | etc.")
        
             | SamoyedFurFluff wrote:
             | Weird take. We know communal lynchings happened; people
             | literally took family photos by them! People happily
             | documented that hangings were the town spectacles when they
             | happened! Let's not play rose tinted glasses about
             | communities before social media: if you were not "in" that
             | group you were vulnerable to violence or death. We have
             | that now, where a disproportionate number of homeless
             | minors are homeless because their parents kicked them out
             | for being gay or trans and, clearly, no one else in their
             | "community" was willing to take them in.
             | 
             | We need to be comparing how communities are right now vs
             | how social media is right now and not some idealized notion
             | of what in-the-flesh communities might be like. Right now
             | we have a dearth of welcoming in-the-flesh community
             | alternatives for people that have been cast out of
             | traditional social groups and use technology to cope. This
             | doesn't mean technology bad. It means society needs to
             | change so technology isn't so tempting.
        
               | jimbokun wrote:
               | Statistically, the mental health of gay kids is worse
               | today than it was when there was a lot more real world
               | persecution.
        
         | ben_w wrote:
         | > Think of self-checkouts, chat-bots, AI partners and
         | therapists, technology making us more self-reliant (which is a
         | bad thing).
         | 
         | When was the last time you used a bank teller rather than an
         | ATM? For me, at least 5 years ago. On the other hand, despite
         | ATMs, I'm told more people than ever work as bank tellers.
         | 
         | > If we keep letting technology take away our communities this
         | way in this two step process (first, take away the community
         | then supply an inferior, superficial substitute), then we will
         | compelely lose our humanity.
         | 
         | I think the process is backwards: the substitutes
         | (superficially better but not really) are usually what cause
         | people to leave local communities. It's video games which take
         | people out of clubs and cause the clubs to close, not a lack of
         | clubs which drive them to video games.
         | 
         | And the disjoint of remote people, of parasocial relationships,
         | isn't new. Let's say you're in St. Paul's Cathedral as a
         | worshiper: it seats 3,500, far more than the Dunbar's number
         | our brains can cope with. The Bishop of London doesn't know all
         | the people present, for the same fundamental reason that
         | someone with 3500 "friends" on Facebook doesn't really know all
         | of them. All well before radio stars and TV, let alone the
         | internet and AI.
         | 
         | So, whatever of our humanity can be killed off by the mere
         | existence of this change (as opposed to deeper things like
         | malicious propaganda), it was already dead long before any of
         | us were born.
        
           | vouaobrasil wrote:
           | > I think the process is backwards: the substitutes
           | (superficially better but not really) are usually what cause
           | people to leave local communities. It's video games which
           | take people out of clubs and cause the clubs to close, not a
           | lack of clubs which drive them to video games.
           | 
           | Yes, that's what I meant. Sorry, I was not clear. I do mean
           | that we have a process of substitute > leaving community >
           | more substitute. I just isolated two steps from this, but I
           | see how that was confusing.
        
             | ben_w wrote:
             | Then we are probably in agreement :)
        
           | vouaobrasil wrote:
           | > All well before radio stars and TV, let alone the internet
           | and AI.
           | 
           | All true, which is why I think we should be cautious of ALL
           | technology, and try and vigorously decide which ones we
           | should use in a process similar to that of the Amish (but
           | without the religion, perhaps). Any discussion would be
           | better than the ZERO discussion that we have today.
        
           | jimbokun wrote:
           | > I'm told more people than ever work as bank tellers.
           | 
           | Any links to this? I find this very surprising.
        
         | ziddoap wrote:
         | This is a pretty exaggerated take.
         | 
         | Technology is a tool, it can be used to increase your social
         | interactions (e.g. finding like-minded groups online to meet up
         | with in-person) or to decrease your social interactions.
         | 
         | You say technology is "destroying communities", but don't
         | acknowledge all of the communities technology has helped build.
        
           | vouaobrasil wrote:
           | > Technology is a tool, it can be used to increase your
           | social interactions (e.g. finding like-minded groups online
           | to meet up with in-person) or to decrease your social
           | interactions.
           | 
           | The number one myth about technology is that it is just a
           | tool. It is a society-shaping force. For example, WhatsApp in
           | Brazil: even if you HATE whatsapp and Meta and don't want to
           | use it, you might be forced to use it if you want to get a
           | job, book a hotel, etc, because it's so entrenched.
           | 
           | Sorry to say, but technology works through first being
           | optional, then being adopted because it gives a person
           | marginal advantages in the short-term, and then being
           | mandatory because the majority adopts it.
           | 
           | Many people are forced to use technology even if they would
           | rather not because if this process. That technology is a tool
           | is the greatest misprepresentation of any concept in the
           | history of humanity.
           | 
           | Edit: let me ask you one question, how did you get the idea
           | that technology is just a tool? How many times to people
           | repeat this mantra? Try thinking about it more deeply and
           | over many decades of time and understand the root cause of
           | this thinking.
        
             | ziddoap wrote:
             | That's a whole other conversation, sure.
             | 
             | My point was that you can (and many people do) use
             | technology to increase their social interaction. You seem
             | to suggest it can only possibly decrease it.
             | 
             | > _The number one myth about technology is that it is just
             | a tool._
             | 
             | I didn't say it was _just_ a tool.
             | 
             | It is _a_ tool, which can be used to help increase social
             | interaction.
             | 
             | > _Edit: let me ask you one question, how did you get the
             | idea that technology is just a tool?_
             | 
             | I didn't.
        
               | vouaobrasil wrote:
               | > You seem to suggest it can only possibly decrease it.
               | 
               | Well, I think it can increase it, but that the increases
               | in time form a sequence of local maxima that themselves
               | are strictly decreasing. (Edit: I meant in terms of
               | overall societal health, like adding up the social
               | happiness of everyone).
        
           | weweweoo wrote:
           | The big picture is that social media and smartphones reduce
           | social interactions, and lower their quality. Just look at
           | all the kids and teenagers that are glued to their
           | smartphones all the time.
           | 
           | Obviously there are exceptions to the rule, like people
           | living in middle of nowhere, or who have otherwise trouble
           | finding like-minded friends offline.
        
           | jimbokun wrote:
           | We have enough data now to confidently say the impact of
           | computer technology on socializing has been a net negative.
        
             | ziddoap wrote:
             | My comment wasn't really about whether it is a net negative
             | or a net positive. I could definitely be convinced it is a
             | net negative.
             | 
             | But my comment was about how the future of having to be
             | drip-fed social interactions to meet our basic needs,
             | otherwise no one will ever interact with anyone ever, is a
             | silly exaggeration.
             | 
             | In any case, I'd love to see what data you're referring to.
             | I'm familiar with studies that look at specific
             | technologies (e.g. social media). But I'm unfamiliar with
             | data/studies that looks at all technologies across all
             | levels of society and measures the net benefit/harm. I'm
             | not even sure how you would go about quantifying, say, the
             | benefit of being able to contact a long-distance relative
             | with significantly more ease and less expense vs. the harm
             | of having to use Facebook to organize the video call.
        
               | jimbokun wrote:
               | I meant specifically availability of a personal smart
               | phone and social networks to young people leading to an
               | increase in mental health issues, as thoroughly
               | documented by Jonathan Haidt. I should have been more
               | specific.
        
         | throw18376 wrote:
         | a lot of people have truly deficient social skills. technology
         | didn't make them this way they're just bad at it, so bad that
         | they can't even have enough social interactions to improve and
         | practice. can't even hold a conversation with a cashier. they
         | simply lack the skills to be part of a community.
         | 
         | ideally such people could build remedial social skills by
         | practicing with a real therapist. but that's costly and
         | difficult to make accessible, because "bad at conversation and
         | annoying" is not a mental illness.
         | 
         | an LLM here could help. just to give someone a sense of how to
         | hold simple, normal conversations and practice very basic
         | theory of mind, to the point where they could start building
         | real social skills.
         | 
         | the problem is whoever builds that system may choose to exploit
         | the users and build dependence. but that's a choice, it doesn't
         | have to happen.
        
         | jimbokun wrote:
         | > Nowadays there is very little real interaction beyond the
         | nuclear family.
         | 
         | What nuclear family?
        
       | alpenbazi wrote:
       | haha, sure, i learn how to be a human with a machine
        
       | helboi4 wrote:
       | Another episode of "what convoluted way can we use tech to
       | 'solve' a social issue that it clearly exacerbates to try and
       | desperately keep the blind cult-like silicon valley version of
       | techno-optimism alive for as long as possible, while ignoring the
       | obvious disastrous social consequences"
       | 
       | I'm pretty sure nobody 15 years ago would have uttered the phrase
       | "opportunities for practising social skills are hard to come by".
       | All social technology ignores our biological need for physical
       | closeness and the severe negative outcomes to our brains and
       | health when we don't have it. People who are so socially crippled
       | that they would be considering this treatment are a symptom of
       | destroyed communities, broken social cohesion, tech addiction and
       | this overly popular brand of post-covid hermitism that seems
       | popular on this site. These are social ills that all need to be
       | tackled. Absolutely nothing about talking to an LLM will help,
        
         | Noumenon72 wrote:
         | A comparison to video games shows how hard it is to truly
         | practice social skills. You can't play the same situation over
         | and over, which is why it's easier to get better at small talk
         | than confrontation. People don't want to reveal how they
         | manipulate you, so schools can't teach about head tilting and
         | brinksmanship. You have few trustworthy external evaluators, so
         | you can come away from a conversation where you talked the
         | entire time thinking you got a high score instead of a low one.
         | The opportunities for using social skills to make a romantic
         | connection are rare and you hardly ever even get to see how
         | other people do it. Being able to act out scripts and get real
         | feedback could be a tremendous benefit to the world.
         | 
         | People who offend, withdraw, or blunder have existed since
         | before techno-optimism. This is their chance to become better
         | in a safe space without embarrassment.
        
         | theshackleford wrote:
         | > I'm pretty sure nobody 15 years ago would have uttered the
         | phrase "opportunities for practising social skills are hard to
         | come by".
         | 
         | You'd be wrong.
        
       | ayushl wrote:
       | tbf its more about training rather than social skills
        
       | VeryFinePrint wrote:
       | As a reddit mod of a tiny community I've very recently started to
       | suggest users use ChatGPT to re-word their comments and
       | submissions when their phrasing is inflammatory. Any point worth
       | making is worth making well. It is still early stages, so I'm not
       | sure how effective it will be.
       | 
       | I've noticed that ChatGPT can do a decent job rewording an angry
       | message to be less toxic while drawing out the salient points.
       | The output it produces a little stiff or stuffy, but I find that
       | preferable to "authentic" toxic messages.
       | 
       | As a mod I find that removals have less sting when you provide
       | the user with an alternative path forward to get what they want.
       | When a removal isn't just a "wall of no", it feels less like a
       | personal rejection. ChatGPT offers a path around that "wall of
       | no" for users by a) showing them what the right way to make their
       | comment is and b) gives them a path/tool to getting there nearly
       | every time.
        
       | lasermike026 wrote:
       | Is it me or are most of these posts written by AI?
        
       ___________________________________________________________________
       (page generated 2024-04-09 23:02 UTC)