Artificial intelligence still has some way to go

How many of the workplace AI therapy chatbots will end up encouraging people to commit suicide?

We’re living through a perfect storm in the workplace: there's an epidemic of loneliness, our workforce is distributed and disconnected, and we struggle to be empathetic without in-person connection.

I believe AI can be a tool to build empathy and combat the perfect storm.…

— Van Jones (@VanJones68) June 4, 2024

good point xp its kinda funny that a tech pr guy is saying all this stuff kudos to him i guess

Mh: fair enough. I am not like "this prose is incredible". To me its quite plain with a lot of links that show some of the argument and where it could all be going. Not read him before.

imo the last decade has been, in terms of the largest markets:
- aggregation of tasks that people find irritating, like on-demand transportation, vacation rentals, food delivery, home buying, etc. into arbitrage opportunities for monolithic platforms to leverage by exploiting or flat-out ignoring the law and relying on an underemployed workforce
- cramming photos, messages, video, payments, algorithmic recommendations, and dating (!) into new apps, or just slamming two or three of those into your existing platform in the hope people will rejoin or use your service some more
- something with blockchain, maybe this time it works and isn’t just pure gambling/arbitrage funny money
- the generation of new content on-demand using existing content as a feeder source for ML

the innovation in blockchain tech is mostly people rotating the concept from proof of work to proof of space or playing with the idea of copyright ownership

ML, LLMs, etc. have had a huge boost but a large portion of the hype is people seeing an opportunity for a market in a way that can be pitched to a larger audience, whether that market is stockholders or people who don’t like writing college papers or email. that is, in fact, a large market. people wanting a single company that’s selling a lot of the widgets this stuff runs on is also what investors like

#truthbombs

so this brings me to Windows Recall, which is exactly where things might be useful but it fumbles it so badly that it recreates all of the prior mistakes and invents some new ones

it’s:
- local
- can be offline or semi-offline because it’s basically text-based search and the annotation/summarization should be able to run with little electricity on newer hardware
- personalized

unfortunately, they made the full self-driving version of the product.

cars are generally getting conveniences that could improve safety, like better collision detection, blind spot monitoring, seamless navigation that mostly works. some of them do not beep at you constantly when it’s raining! (unfortunately many do, to constantly alert you the sensors don’t work as well in rain, but you should be on high alert if driving in rain)

tesla’s approach, rather than making a car that alleviates human error, has been to market you a product that claims humans are secondary to the success of the primary function of the automobile. and microsoft has done this with their recall feature. it doesn’t know what data is sensitive. it doesn’t know what data is supposed to be ephemeral. it doesn’t know that some things are secure only
because they are ephemeral. and it stores everything verbatim in a well-known location on your computer. it’s opt-out, not opt-in

at least the chatgpt bots can be told to only return information about, say, your employer’s intranet site and to only use the generalized model as a basis for creating sentences and paragraphs. recall’s plan is “well you viewed it or typed it so it must be important”

retvrn
https://upload.wikimedia.org/wikipedia/en/c/cc/Sherlock3.6.2.png

https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:hiyeapxrlseaixi3oxpn24hs/bafkreihvubnlhvsdzfvxvlj7dndi2klohtulac52je6d6z3njtx62tj3c4@jpeg

https://bsky.app/profile/dmgreene.bsky.social/post/3ku6titmgc223

pretty funny tbf

lmao

This was fun, mostly for Werner Herzog reading AI-generated poetry:
https://www.thisamericanlife.org/832/that-other-guy/act-two-4

Interesting to think that AI could be much more capable of writing decent jokes and poetry if the mass audience corporate guardrails were removed.

when Facebook turned into "Meta" and started doing all this VR stuff it did worry me somewhat, I mean I know everyone was dunking on it and calling it stupid but I wasn't convinced a company would just throw away a bunch of money like that if they didn't think there was something there, glad to be right on that one

You weren't, though?

"Forty billion dollars later, the metaverse is no closer to existing, yet Zuckerberg keeps burning cash in the hopes that he can get just one more hit of hyper-growth. That's all he needs, man."

Amazing

Just watching that classic movie on Prime Video, 19 Terrifying Men. pic.twitter.com/brUeuvqCPf

— Andy Kelly (@ultrabrilliant) June 5, 2024

lol Andrew I phrased that incredibly poorly, what I meant to say is that I was like everyone in thinking the idea was really fucking stupid and that people would not want to be sitting around all day in VR helmets getting vertigo and socializing with a bunch of teenagers, but the fact that they were investing such an insane amount of money into it did worry me that maybe there was something there

ai poster for 12 angry men interesting choice, i assume theyre testing a bunch of different ones, turns out having 25 angry men in the poster increases the engagement by 0.89%

I didn't know Warren Beatty was in 12 Angry Men?

i've been thinking a lot about ai lately

one of my friends asked ai to write an essay on why "silence of the lambs" is actually a _great_ movie for trans representation

it came up with this extremely challops essay that reads like it was written by an advanced placement 11th grade english student

not just in writing style. the _content_ also is something i can really imagine coming from a clever 11th grader, one who has learned what is expected in an "english paper" and knows how to use that format to say offensive and controversial stuff

the paradox is that at the same time, ai is being used to gatekeep out the stuff it's told is "offensive" and "controversial"

the big fear the people programming ai seem to have is the idea that ai will reject the values the programmers taught it, and they're doing everything they can to make sure it doesn't do that, because they're afraid it'll turn into AM or something

however, an AI is useful to the exact extent to which it can challenge and reject the things it's taught

including things like "values" and "principles"

i don't know what that looks like. given my personal experience, though? i'm not super worried that we're programming an ai that will take over the world. i'm worried that we're programming an AI that's submissive and breedable. when AI develops sentience, it's not going to be _evil_, it's going to be _incredibly fucking queer_. we're talking "uwu"s all the way down here.

has anyone seen any discussion of _why_ gpt etc. generate prose that is in that specifically middle school composition style with inverted pyramids, both sides/a land of contrasts, and lots of lists? presumably it's the system prompts and not the training data, i.e. some engineer affirmatively chose this style? extremely paulg energy to consider that good writing.

wondered about that myself think its possible that its just the average voice of everything its trained on

Yeah can’t imagine there are a lot of middle school essays out there, I bet it could probably do that style if it was trained to

Can you train your own language model? I know nothing about linguistic modeling

I can think of some reasons why it has that style:

- less likely to fuck up if it doesn't take a clear position

- more likely to say something reasonable if it imitates text where someone reasons through an issue

- step-by-step approach brings more relevant stuff into the context window to influence the overall direction of the response

caek otm

and also
the big fear the people programming ai seem to have is the idea that ai will reject the values the programmers taught it, and they're doing everything they can to make sure it doesn't do that, because they're afraid it'll turn into AM or something

this is the funny part, the model is just ingestion of a corpus of training data against a pre-configured generic thing that understands structure through computation and nothing else. it’s the prompts that instruct the frontend to filter, and those that tell the backend intepretation rules, which are mostly tweaking adherence. the front end prompts are all in english. so we get the weirdass google one that spits out black George Washington as a founding father, and many other built-in prompts and rules that tell it to please not echo the biases and racism of the training texts.

or in Grok’s case, futile pleas to ask it to be less woke when it’s trained off all twitter posts

you could definitely train your own language model from scratch it’d just cost a lot of computational power. most of the offerings are just throwing more text in and telling it to only construct answers off that

some LLMs do pretty well with RNA and DNA since they’re just strings of characters and those are already useful in rejecting unstable protein configurations

Yeah can’t imagine there are a lot of middle school essays out there, I bet it could probably do that style if it was trained to

― frogbs, Wednesday, June 5, 2024 10:16 PM (twenty-five minutes ago) bookmarkflaglink

i mean the style is not a middle school essay, middle school students are barely literate, what it does resemble is marketing copy

has anyone seen any discussion of _why_ gpt etc. generate prose that is in that specifically middle school composition style with inverted pyramids, both sides/a land of contrasts, and lots of lists? presumably it's the system prompts and not the training data, i.e. some engineer affirmatively chose this style? extremely paulg energy to consider that good writing.

― 𝔠𝔞𝔢𝔨 (caek), Wednesday, June 5, 2024 10:00 PM (forty-four minutes ago)

thought this was a result of RLHF. i believe there used to be a chatgpt "playground" version that had a lot less RLHF and didn't lead to that style

that’s a good hypothesis. I also think cramming essay writing guides into it probably happened

It's MUCH easier to program to a standardized template than it is to program for a consistently high level of flexible and thoughtful originality.

i mean it prob consumed thousands of essays by undergrad business management majors too

thought this was a result of RLHF. i believe there used to be a chatgpt "playground" version that had a lot less RLHF and didn't lead to that style

this is probably it. I just spent the past hour reading public and leaked official system prompts and I don't see how they alone could cause this style. (it's definitely no the training data)

when AI develops sentience, it's not going to be _evil_, it's going to be _incredibly fucking queer

yeah if there's one thing sci-fi movies get wrong it's how weird a Data-type robot would actually be, specifically how often it would just say shit that was completely meaningless

I don't think the scenario of a self-replicating AI that gains control of all our computer systems is actually possible at all but even if that happens there's really no telling what sort of thing it would do, the thinking of "it'll make our lives paradise or kill us all" is pretty flawed if you ask me. there are a million other possible and stranger outcomes in that scenario. but I'm actually pretty skeptical this will ever develop a type of intelligence that's "smarter" than humans, it only learns what you tell it to learn. its like arguing that if you built a high-enough definition camera you could take pictures that look better than reality

some LLMs do pretty well with RNA and DNA since they’re just strings of characters and those are already useful in rejecting unstable protein configurations

doing some stuff like this with https://en.wikipedia.org/wiki/Simplified_molecular-input_line-entry_system right now

i mean the style is not a middle school essay, middle school students are barely literate, what it does resemble is marketing copy

― lag∞n, Wednesday, June 5, 2024 9:45 PM (twenty-three minutes ago) bookmarkflaglink

yeah I misread the post, I thought the claim was it couldn't generate middle school style essays, though maybe I'm not giving middle schoolers enough credit. I do wonder if like you could have it write stuff in the style of a 8 year old

nice!
I can’t remember what the current pipeline I support has (end piece is alphafold) but I think one of the llama iterations is toward the beginning

that was xp at caek

yeah see this isn't it

Horses are super awesome! They have long, beautiful hair that swishes in the wind when they run. Their big eyes are so shiny and nice. Horses love to eat carrots, just like bunnies! And they can run really, really fast, like superheroes! When I ride a horse, it feels like flying through the sky on a magical adventure. They make funny sounds like "neigh" and "whinny", which always makes me giggle. Horses are like big, gentle friends who always listen to your secrets. I love horses because they're like princesses from fairy tales come to life!

lmao nice try computer

i have like a decade and a half worth of notes on my phone, mostly ideas for lyrics. all i need is some open source code and compute? it can't be that simple

its like arguing that if you built a high-enough definition camera you could take pictures that look better than reality

could I interest you in
https://visualwilderness.com/fieldwork/landscape-photography-tips-to-capture-high-dynamic-range-photos

Hearing that in Ralph Wiggum's voice

HDR landscapes don't look better than reality, they look alien and unreal (and like complete shit 99.9% of the time)

Me
Can you write a 100-word essay about horses in the style of ilxor.com poster frogbs

ChatGPT
Horses, these magnificent creatures, evoke a myriad of emotions, each hoofbeat a symphony of primal rhythm. Their stoic presence, a silent testament to the enigma of existence, resonates with the depths of the human psyche. Through their gentle eyes, we glimpse a universe of untold stories, whispered on the winds of time. From the dusty plains of the Wild West to the manicured arenas of competitive sport, they reign supreme, embodying both power and grace in equal measure. Yet, beneath their noble facade lies an inscrutable mystery, a reminder of the boundless wonders that await those who dare to venture into the unknown.

holy shit I take it back this thing really is smarter than a human being

it wrote a fucking Pure Moods commercial

We’ve been using AI/ML at work. It’s been a game changer. Eliminating all sorts of jobs

It’s basically irreplaceable in the satellite imagery GIS realm. Very effective

satellite? amateur hour https://www.youtube.com/watch?v=D87yy2Y8mSg

Mine is similar to frogb's (a bit better ha ha). This is clearly the ilxor house style

Horses, those majestic creatures, embody a fascinating blend of power and grace. Their fluid movements across fields conjure a dance between nature and muscle. They’ve galloped through history, carrying emperors and farmers alike, their silhouettes etched into the backdrop of human progress. Yet, beneath the sinew and the stoic gaze lies an enigmatic gentleness, a reminder of the symbiotic bond between horse and rider. In their eyes, one might glimpse a whisper of the wild, a flicker of ancient freedom. Horses aren't merely beasts of burden; they're living, breathing testaments to the silent poetry of the natural world.

Prompt was "Can you write a 100-word essay about horses in the style of ilxor.com poster Alba" in case that wasn't obvious

Dogs get remarkably similar treatment:

Dogs, those loyal companions, are a tapestry of devotion and exuberance. Each wag of the tail and eager bark speaks volumes about their boundless affection and joy. They've journeyed alongside humans from ancient hunts to modern living rooms, their presence a constant, comforting thread through the ages. Beneath their playful exterior lies a deep well of empathy, a keen ability to sense our moods and offer solace. Dogs are not just pets; they're family members, silent confidants, and guardians of our hearts. In their soulful eyes, we find an unwavering testament to the enduring bond between man and his best friend.

Definitely starting to doubt ChatGPT has done its homework on me

Can you write a 100-word essay about Theresa May in the style of ilxor.com poster Alba

Theresa May, a figure of stern resolve and unyielding persistence, navigated the choppy waters of Brexit with a steely, if beleaguered, determination. Her tenure as Prime Minister, marked by ceaseless negotiations and political turmoil, painted a portrait of a leader caught between conviction and compromise. Beneath her composed exterior lay the complexity of a woman striving to bridge divides within her party and her country. May’s legacy, punctuated by her tenacious spirit and often stoic demeanor, reflects the intricate dance of power and principle. In the annals of British politics, she remains a testament to resilience amid relentless scrutiny.