Artificial intelligence still has some way to go

I can't wait until every article is written in the format of a 9th grade paper about the Civil War. Gimme proper introductions and conclusions or gtfo, I says.

I was finding guides to using the chatgpt api that were written by chatgpt.

I twigged when I just decided to ask chatgpt

It's like Human Centipede but where ChatGPT's mouth has been sewn to its own anus.

I would ask chatgpt for a fuller description of the chatgpt centipede, possibly with a dall-E illustration, but unfortunately it is down

The robots have not thanked me, as far as I know. And when I am unemployed, probably next month, they will not pay my mortgage. So forgive me if I am little bit bitter about that.

― Oh I believe in Yetis' Day (Ye Mad Puffin)

ai is going to wind up taking more and more jobs... not just directly! the ones that are left require an ever-changing set of skills... it's really hard for me to continue to keep up with what's considered "employable" these days. i am seeing a lot of people in the same boat. people get laid off and finding a new job is just really difficult these days. a lot fewer jobs. a lot less money. plus, a lot of my friends are "disabled" and not able to work. the economic and social values i was taught was that people who aren't actively working are a drain on society, a burden. if they're suffering, well, it's their own fault. that's what i was taught. those are the values i see being put into practice.

these aren't values i particularly agree with. i don't think that these values are... a viable basis for a society, on a long-term basis. i don't have the power to change those values. it's a major source of ongoing stress in my life. i employ a lot of radical acceptance. i'm getting a lot of opportunity, these days, to practice radical values.

anyway i'm not going to throw one of my shoes at gpt. those things are fucking expensive, i need me some shoes.

American capitalism is based on a covert “deal.” Work hard and you will find a niche where you “provide value to shareholders” and then you’ll get paid so you don’t starve. This deal was never actually true, but for many people it looked more true in the past than it does now. And so the question is what will happen when more people acknowledge that the old covenant is *really* broken this time. There is no path to living in comfort and dignity for many.

So much of politics and ethics in america is built on what you described kate. The idea that if people were willing to work they would at least prosper moderately. If chat gpt destroys, say, 80% of lawyers’ jobs all of that kind of thinking is going to seem laughable, even to the formerly comfortable middle and lower bourgeoisie.

It could be a revolutionary moment. More likely America will just become colder and angrier.

im gonna wait til ai demonstrates 5% of the competency required to do a job before i start worrying about it taking them

Best case scenario, people stop valuing human beings for what they can “provide” and start appreciating them for their intrinsic value. The kantian imperative. And then we build new economic and political structures around this humanistic framework. The odds seem long for this one though.

also worth noting that software and indeed technology generally has been "taking jobs" for a long time, are there fewer jobs now, not really, are the current jobs worse, yes in a way, specifically in the way that they pay less offer less security etc, is that because the jobs technology took were inherently better, was file clerk a somehow great job, no, the issue with downward mobility amongst working people is of course one of worker power, and corporate power

if you want the kantian imperative you have to join a union, then you can ask them for it lol

interesting question is ask people what job their grandfaters did if they owned a house if their grandmothers worked, tho this may be more of a great grandfather question for some people at this point, couple memorable answers ive gotten for home owning sole bread winners were worked at a news stand and donut maker

I am in a union xp

nice

My paternal grandparents owned a house in rural Indiana, where they ran a small restaurant. My maternal grandparents lived across the street from them. My mom's dad was the town doctor.

I visited recently because my uncle passed away. The lawyer who was handling the estate said that my grandfather had delivered her as a baby.

my grandfather was born on the farm our ancestor bought with money from the gold rush, america gotta love it baby

More likely America will just become colder

Wait I thought the leading doom scenario was about things getting warmer.

ayyyyyy

My grandfather made suits, and there's a family story that he won a contract to make uniforms for the Chicago Police in a poker game.

AI only does what you ask it... it's not quietly thinking of new products, new films, new ideas; it just responds to input and barfs out a facsimile

There is no force that drives the fuse

I agree. The question is how many jobs require simply regurgitation of that kind. I personally don’t know.

I don't disagree in principle - certainly that human intervention is currently needed, a lot - but I'm a bit more pessimistic about how much of the world of work straight statistical mimesis can eat, especially as gen ai improves.

I agree. The question is how many jobs require simply regurgitation of that kind. I personally don’t know.

the stumbling block for the automators has been that people

It’s a paradox though because while automation causes individual firms to save money and increase profits, in the end it causes the economy to shrink.

I think. Wouldn’t it cause a crisis if unemployment drastically rose? Who would be spending money on goods and services?

https://en.wikipedia.org/wiki/Tendency_of_the_rate_of_profit_to_fall

i mean the economy has grown quite a bit since automation started

My understanding of this is incomplete (intentionally, for reasons already discussed). But didn't Open AI stop collecting new information a few years ago?

As a result, AI's assumptions are incomplete at best, and at worst will just get more and more outdated.

To be useful in future, it will need more humans to fuel it and give it more IV injections of that sweet, sweet, content. Yeah baby (I hear it saying), feed me content.

We are all Seymour from "Little Shop of Horrors."

what if the ai apocalypse is just the machines forcing us to make more content, which we were doing anyway

Trenchant

I will go in to work tomorrow and cheerfully type for my robot overlords. Because it's not like I have a lot of other choices.

Personally I am too old to shift gears and become, like, a useful member of society or whatev

If it's dumped onto the internet anywhere it's all fodder for LLMs, because copyright doesn't apply to how AI munches on its manifold inputs, digests them, and creates its mindless homogenized sentences. We ilxors converse openly about whatever interests us and consequently we are ingested. It even applies retroactively and involuntarily to conversations long before these chatbots existed.

My understanding of this is incomplete (intentionally, for reasons already discussed). But didn't Open AI stop collecting new information a few years ago?

The version anyone can use has a training cut-off date (currently April 2023). But behind the scenes newer models are being retrained & they'll be up to date, tho I don't know what the deal is with the presumably significant problem of it being fed its own shit.

Can users customize an ai dataset? I’m curious about an AI trained solely on the ilx archives. Would they be chill? Would they be an asshole? Would their prose still seem like an alien wrote it while wearing a human suit?

AI Centipede

xp

didn’t I post a few times about how people add data sets and knowledge bases to ChatGPT/llama/etc or am I taking crazy pills here

fwiw the entire shtick we’re all doing where we ask it questions and assume it’s giving facts of some sort is just a side effect of how it works. it’s overall irrelevant, or supposed to be, to their business model that ChatGPT spits out things resembling facts, afaict. it’s just a chatbot that can string together language in a human-like manner. GPT as a product that you license and plug your own factual data in is supposed to be the value add

Can users customize an ai dataset? I’m curious about an AI trained solely on the ilx archives. Would they be chill? Would they be an asshole? Would their prose still seem like an alien wrote it while wearing a human suit?

― treeship., Wednesday, November 22, 2023 7:52 AM (one hour ago) bookmarkflaglink

yeah its not too hard if you know to c0de a lil bit, the computer geniuses have done all the heavy lifting you just need to feed it the training data, scraping and tiding up all the ilx posts would prob be the most difficult part

maybe theres even some more non technical interface out there idk

iirc ilx search uses the Lucene library, although I don’t remember what the persistent storage for the indexing is. pretty standard and people appear to have libraries or plugins to bridge that to GPT

you be funny if you trained it on full ilx threads just to see what user names it came up with when its making its post

ethereal brigadier lethbridge-pfunkboy

the whole AI/automation panic makes me wonder what jobs there are out there where you learn a stock set of skills and never have to learn new tools, techniques, etc

my friend’s prior job had a couple peers who were told to do some online training and one guy went nuts. saying he didn’t have time, he was getting close to retirement, he was busy at home. he ever blurted out something like “I don’t need a raise just let me keep doing my job!”

absolutely dead-end crazy ranting. the funny part was that the training was online and they were allowed to do it during work hours, and the group was not that busy!

Openai released a non-coding custom dataset solution a couple of weeks of ago - they're confusingly called GPTs but you can just feed it a knowledge base and give it custom instructions. I think the additional stuff you can add is comparatively small - I read 300 pages somewhere but I have no idea what a page is in this context. idk dig around

yes haha yes

OpenAI Employees Say Firm's Chief Scientist Has Been Making Strange Spiritual Claims

https://futurism.com/openai-employees-say-firms-chief-scientist-has-been-making-strange-spiritual-claims

its very funny that these people have produced nothing that resembles artificial intelligence and their tech certainly has no hope of ever getting there and yet they feel like theyre just on the edge of some world changing event, it is kind of a religious situation

saw a chart a while ago saying that american participation in organized religion had dropped 15% in just the last ten years, between this ai shit and taylor swift fans i think maybe people should just go back to church, its all set up already go once a week and get it out of your system

xp lol this story is fun all the way

and yeah as mh and lag∞n say I think it wouldn't be that hard to take a model and retrain it on a big scrape or dump of ilx. But you might need a lot of computing power, money or patience?

assume everyone knows GPT is definitely trained on ilx already. But it's such a tiny part of the data - if you try to get it to mimic ilx style it can describe the tone it is aiming for but the results are not good (I won't clog up the thread with more chats).

i realise this is creepy but i’m hoping we get to that black mirror / house of usher tech soon where i can feed in someone’s social media history, emails, etc and get a reasonable facsimile of their vibe so that i can converse with them when they’re gone. sure it’s not them, but if it’s incorporated all their text it kinda is them, for certain purposes, and yknow if we can fool ourselves into thinking dogs have souls it can’t be too much of a jump to feeling a sense of a connection with a bot tuned to the frequencies of a loved one

youre saying you want that

yes!!