Artificial intelligence still has some way to go

It is nothing without the data.

A couple decades ago when I wrote simple natural-language programs as a hobby (it would overestimate them to call them AI) I soon arrived at the conclusion that any intelligence such programs might be able to display would reside exclusively in the data. Nothing I've seen since has changed my mind. What makes these so impressive is the size of the data set they are able to manipulate.

I don't know, I told it to combine a Goya painting and a photo of a spider and got this, seems quite novel:
https://pbs.twimg.com/media/FvWLnEyacAAsqIW?format=jpg&name=small

I am mostly being facetious.

Try prompting it just to "create a novel image of a spider" and see what it can produce. Your creative prompt and the imagery in its data set provided almost everything you see there. The program provided the algorithms that recognized your prompt, selected imagery that matched your prompt, and statistically reworked the selected images into a single image with blazing speed, which I grant is damned impressive and amazing, but without that vast data set of correctly tagged images nothing at all would've happened.

Gotta say the visual imagery generating programs have improved since 2020, as shown by the Twitter feed ulysses linked earlier in this thread:

Artificial intelligence still has some way to go

The rate at which it has advanced is stunning, that’s true.

I've seen plenty of cool midjourney images but I feel like it's gotten so good that the results end up being a bit too clean and not as weird and "artistic" as some of the previous image tools.

Some ok points here except it spends way too long on bunk like accelerationism and doesn't talk about offshoring operations.

https://www.newyorker.com/science/annals-of-artificial-intelligence/will-ai-become-the-new-mckinsey

xp yeah I thought about that when I pulled out Bright Green Field by Squid the other day, since the cover and inner sleeves are all AI-generated images that look blurry and weird. it got so good so fast I honestly thought someone was trolling with art that they had made.

xp good piece, thanks for posting that. agree on the accelerationism bit though; if your two citations are Susan Sarandon and Zizek, maybe the point isn't worth bringing up

This one is interesting. It seems like the mansplainer knob has been turned down and the empathy know turned up

https://heypi.com

Interesting that it can remember chats from across multiple days as well

"interesting"

this may have been posted in the achewood thread as well, idk

https://raybot.help/

I think GPT is simultaneously fascinating for how amazing it is, how terrible it is, and the particular ways in which it is terrible. It's the greatest bullshit machine ever invented. I occasionally ask it legal research questions, and it will often give me what is generally a pretty decent response except it nearly without fail invents all of the cases (complete with properly formatted fake citations). In fact, I don't think it has ever given me a case that actually says what GPT claims it says, and often the cite is for an entirely different case. The exception seems to be on well-known cases that have been written about, e.g Supreme Court opinions. It's decent at summarizing those, though it often misses anything beyond the 10,000 foot view of the holding.

I mean the fact that it can do what it can do at all is fucking astounding. It's sort of like we just invented a laser that can instantly shoot through 10 feet of steel but we're complaining that it can't go around corners. But it can't go around corners.

Similarly, it just gave me this highly specific, detailed, and fully plausible sounding summary of a recent DOJ settlement that didn't actually exist. When I questioned it, it changed the dates and details, but it still didn't exist.

https://pitchfork.com/thepitch/musicians-are-already-using-ai-more-often-than-we-think/

super psyched for music to become exclusively derivative mashups

Wonder if that is what was responsible for the weird version I heard the other day of “Southern Man” by John C. Cale and Nico Nico.

Dave Clarke posted this yesterday:

Had an email offering AI production for Techno , flat fee and ownership to be mine. We have had ghost production for quite some time now but this is a new phase. Following the path here could mean that AI algo chart shaping is monitored by AI track making and then machine eats machine…. Shame that art is being devalued.

He doesn't sound 'glad all over' at the prospect

Lol

Still far from sure if this is the beginning of the end or just a passing hoax craze

https://www.independent.ie/irish-news/irish-times-removes-article-suggesting-fake-tan-is-racist-amid-suggestion-it-was-ai-generated/a289268428.html

Been doing a trawl on the AI vocal tracks on YouTube.

They range from
1. Terrible gibberish
2. Suspend disbelief, maybe
3. That's just a Michael Jackson impersonator with a backing track

Like, you could make a C90 of "Yesterday" fakeys

The AIsis one is easily the most successful.

https://foodly.tn/tips/why-do-cracker-barrel-waitress-get-stars/

ai has arrived. this page answers every question

This made some ok points:

https://www.theguardian.com/commentisfree/2023/may/15/artificial-intelligence-cynicism-technology

"To stay sane, I have had to abide by twin principles: I don’t believe it until I see it. Once I see it, I believe it."

Having said that, I think this is the bad point. You gotta look at the thing and sometimes make a judgement call that not just yes or no but maybe. People do think that it's a few notches away from improving things so that a machine could automate a job here or there. There is a lot of research being poured into automation, and even if it's a trick as long as the value of the job is bought down so that people can do it more cheaply it could be enough.

Remember when WeWork would kill commercial real estate? Crypto would abolish banks? The metaverse would end meeting people in real life?

No?

it does make some decent arguments but yeah framing it like that is silly. Crypto and Meta were obviously dumb ideas from the start which got dunked on constantly, and even still you could argue that Crypto still succeeded beyond anyone's wildest dreams, even if it did wind up leaving a lot of unfortunate rubes broke. AI on the other hand is clearly a real paradigm shift, something which may end up not replacing a ton of jobs but will clearly replace a lot of workflows. If it reminds me of anything it's the self-driving hype from 5-6 years ago, which seemed at first like it was going to revolutionize (or even destroy) the entire trucking/taxi sectors, which turned out to be a wee bit more difficult to pull off than it seemed at first. I think a lot of the concerns about AI hinge on the idea of it being able to interface well between multiple applications and codebases, and if you work in IT you'd know how incredibly hard that is. it's the reason why NFTs were such an idiotic idea, anyone who actually believed these things would allow you unique privileges/powers in a variety of games has clearly never worked on one before. which brings up another bone I have to pick with this article - "Elon Musk is clearly great at technology"...really? the guy whose code famously had to all be completely rewritten the instant he left Paypal? The guy whose cars are constantly falling apart with issues that literally no other auto manufacturer has ever had to deal with before? The guy whose dumb decision making singlehandedly caused his rocket to explode resulting in an environmental catastrophe not even a month ago?

Yeah that’s pretty much my take. I am a lot less skeptical of the transformative potential of GPT type AI than I was of crypto, the metaverse, etc. But I also think there are a lot of steps in the chain of things that would need to happen for it to really take over most “knowledge work” or whatever, and that there could be bumps or roadblocks.

It's not good enough to replace people but plenty of CEO types are dumb enough to think it is and use it as such, replacing people anyway. Already been plenty of such journalism cases.

I work in comms and am already using ChatGPT to do rough drafts and have heard plenty of anecdotal evidence of people in other professions using it, so it is already transforming things. Too early to say whether it will actually replace jobs, I suspect a bit but not a lot. It's never going to produce high-grade usable copy straight off the bat without some human intervention is my feeling.

i am half expecting the clowns at my company to try and use it to make significant amounts of training material and eventually phase us out. even though they only created our position 5 years ago.

id' be worth the layoff and ensuing poverty to watch them try and fail.

i will never use chat gpt for a first draft of anything. i don't care how good it gets. i also don't care if all my freelance work dries up because i can't make deadlines like other writers.

it is my enemy -- the enemy of humanity.

all it can see are patterns in the data. generalizations. schemata. stereotypes.

we all use these things too but as a heuristic. our categories are always complicated by our knowledge that they never quite fit. the world exceeds our understanding but it always provides us with opportunities for looking at things in a new way.

this machine has no such capacity and will not. ever. if it produces novel outputs, it arrives at them through a different means. it doesn't touch reality.

this all sounds melodramatic but it is how i feel.

i hate getting student work that was written by it, the glib competence.

we had an assembly today where some teachers talked about potential uses for gpt in our profession, like letting students use it as a first draft, or maybe using it ourselves to change the lexile levels of difficult texts. "it's here and we need to adapt" was the message.

no. never.

it's not even about being afraid it will replace jobs. i am worried about that, but my hatred of this technology is far more visceral.

I suspect you're tilting at windmills there, Treeship! No, it's never going to write a good or original novel. But it may help with some humdrum web copy, or maybe class planning for a teacher. In any case, I'm guessing it'll soon be as hard to avoid as say Google search is today.

i am afraid of a world where people are interacting with the outputs of this stuff all the time to the extent that it shapes their thinking, subtly and insidiously. like, looking at ai generated models in ads all the time doesn't seem that different than looking at airbrushed models in ads all the time. but it is different, i think. same for reading shitty, derivative web copy written by a human versus reading the same thing generated by ai. there are no cracks in the facade with this stuff. it is only derivative product, only a reworking of what came before.

i am afraid of this world and will probably never cease to be

xp I think I agree with all that, but sometimes what you actually need to produce is some derivative reworking of what came before! There's some really dry, boring marketing crap I have to write in my job sometimes, and if AI can help with that, I'm OK with it!

treeship you literally sound like a 14th century scribe who is angry about printing presses

no shade at treesh at all but i about spit my soda out, thx sleeve

I had a lot of the same conerns but they faded a bit after actually using ChatGPT for an hour and seeing how sterile and boring everything it spits out is

i started the Talk to ChatGPT thread and got bored of using it in less than a month

I haven't seen chat gpt produce something enjoyable to read, but it can do a fair job of organizing a set of decent points into a basic 8th grade level essay. It's hard for me to see that replacing any type of writing that people seek out because they enjoy reading. Maybe someone will figure out how to make it churn out something that is stylistically pleasing and original, who knows?

Yeah I don't really think the soul of humanity will be lost if we let a robot do the first draft of, like, a hoover instruction manual, but I do find treeship's hardline stance here very romantic.

Ah, to be young.

Remember when WeWork would kill commercial real estate? Crypto would abolish banks? The metaverse would end meeting people in real life?

No?

― longtime caller, first time listener (man alive), Monday, 15 May 2023 bookmarkflaglink

I remember some marketing like this. One or two countries were playing with using crypto as currency and the like.

Meta is definitely sold as 'no need to meet people in real life'.

I don't remember the WeWork hype.

Yeah I don't really think the soul of humanity will be lost if we let a robot do the first draft of, like, a hoover instruction manual, but I do find treeship's hardline stance here very romantic.

chatGPT is becoming a real engineer pic.twitter.com/3aTXYgLki2

— gaut (@0xgaut) May 15, 2023

hahahaha amazing