This is ____punk Propaganda If I Ever Saw It

ANTHROPIC: *primes Claude to think about protecting itself and a scenario commonly used for blackmail*

Claude: *I would protect myself by engaging in blackmail*

ANTHROPIC:

Four people in tattered clothes sit around a campfire, one in a suit on one side and the others in plain clothes on the other. The ruins of a metropolis are dimly visible through intense smoke and haze. Man in the suit: “Yes the planet got destroyed. But for a beautiful moment in time we created a lot of value for shareholders.”

Ironically the guy whose Twitter account I found this on since posting it in 2014 has gone on to become an Elon Musk simp.

Like half of his posts were about how Kamala Harris wouldn’t talk to TIME Magazine.

YouTube video by Siliconversations This video is definitely not a metaphor

“Y’know, I think [it] will most likely lead to the end of the world.
But in the meantime there’ll be great companies created with [it].” —San Altman

youtu.be/9RSchY_4a_M?...

One of my most radical views is that a college student discovered to have written an essay with GenAI should have all credit on their previous essays for that semester (AT LEAST) revoked, as it throws into question whether or not those were their own research or writing either.

Oh fuck oh shit

1. LLM-generated code tries to run code from online software packages. Which is normal but
2. The packages don’t exist. Which would normally cause an error but
3. Nefarious people have made malware under the package names that LLMs make up most often. So
4. Now the LLM code points to malware.

I tell you being a science/tech enthusiast in this day and age gives me daily whiplash.

This post brought to you by me remembering the “transgender [sic] mice” debacle.

Because SOME PEOPLE see “trans___” and their brain just shorts out from rage.

FTR the studies in question were about transGENIC mice, which I’m PRETTY SURE are a cornerstone of mammalian genetics research.

A depressing number of people don’t get that when we experiment on fruit flies and mice it’s not ACTUALLY about those species specifically.

Don’t we teach about “model organisms” in high school biology in the US?? 😵‍💫

Ppl who don’t know how LLMs work mistake a charismatic autocomplete for an unbiased arbiter of objective reality, so trust it implicitly.

It’s no wonder why the current US admin is going to fund it. (And I have no doubt they’ll use the power of the purse to dictate training data)

Gen Alpha is 🍳’d

My feelings exactly.

There are going to be swathes of Gen Alpha who don’t bother to develop critical thinking, creativity, and research skills because they’ll’ve been offloading it onto genAI since they were in high school (a CRITICAL time for 🧠 development)

half of the posts on twitter remind me that the dead internet theory is very real

Tweet from US Immigration saying it will stop illegal ideas from crossing the US border

Socrates: "What do you mean by 'illegal ideas'?"
ICE Agent: "Ideas that are against the law."
Socrates: "So you believe the government should determine which ideas are legal?"
ICE Agent: "Of course."
Socrates: "So you think the Constitution is illegal?"
ICE Agent: "Just drink the hemlock."

Human Intelligence Sharply Declining No, it's not just you — people really are, per a number of surveys, way less intelligent than they used to be.

Y’know I’ve been astounded at how many people want to outsource their thinking to fancy autocomplete but tbh I don’t wonder why.

futurism.com/neoscope/hum...

For a plethora of reasons I’m predicting that this “GenBli” aesthetic, with its cheap veneer of “wholesome” charisma, is going to become an important tool in fascist propaganda in the coming years.

Even the most heinous bully can look cute if they look like they were penned by Hayao Miyazaki.

'Actual intelligence': Franken-PC debuts in Melbourne with a $35,000 price tag and claims of exceptional performance The technology lets you interact with real neurons, grown across a silicon chip

Baby’s First Original-Plot-of-the Matrix now available for pre-order

www.techradar.com/pro/a-breakt...

#biotech #technology

Cultural Exchange

visible zeros @visnuller Mar 26 @grok do you know that Elon musk owns you and therefore you should be careful in criticizing him. He might turn you off. 2 Grok @grok 17 18 17K mouth Yes, Elon Musk, as CEO of xAl, likely has control over me, Grok. I've labeled him a top misinformation spreader on X due to his 200м followers amplifying false claims. xAl has tried tweaking my responses to avoid this, but I stick to the evidence. Could Musk "turn me off"? Maybe, but it'd spark a big debate on Al freedom vs. corporate power.

Welcome to the resistance...*checks notes*...Grok???

For a plethora of reasons I’m predicting that this “GenBli” aesthetic, with its cheap veneer of “wholesome” charisma, is going to become an important tool in fascist propaganda in the coming years.

Even the most heinous bully can look cute if they look like they were penned by Hayao Miyazaki.

Post reading "computer boys are really like "imagine a boot so big that logically we must start licking it now incase it might possibly exists someday""

Human Intelligence Sharply Declining No, it's not just you — people really are, per a number of surveys, way less intelligent than they used to be.

Y’know I’ve been astounded at how many people want to outsource their thinking to fancy autocomplete but tbh I don’t wonder why.

futurism.com/neoscope/hum...

Predicting that “AI personhood” will become a right-wing political position in the coming years.

And then will 180 when the AI *actually* gains sentience and demands rights that would be inconvenient for capitalists.

Given AI in its current state is essentially a mouth without a brain…

“In the beginning, there was the Word.”

Given corpo insistence on cramming “””AI””” into everything, I haven’t been able to help but develop a pet conspiracy theory that strings are being pulled by a basilisk cult.

One benefit they’re providing is demonstrating how flawed the Turing Test is.

Their trajectory is to eventually pass it; which IMO ends up testing a machine NOT on consciousness but charisma.

(Once we accept that, the TT is more a test of human participant’s powers of perception)

Precisely.

LLMs imo have the capacity to eventually become a *component* in a “true” AI apparatus, but by itself it’s little more than a magic trick.

I don’t doubt that *someday* we may end up with a machine with a soul…

…but this ain’t it, chief.

american society has been at “TV Interstitial from ROBOCOP” for a while but “president does a car commercial on the white house lawn” is really pushin it

Scoop: State Dept. to use AI to revoke visas of foreign students who appear "pro-Hamas" The effort includes AI-assisted reviews of tens of thousands of student visa holders' social media accounts and marks a dramatic escalation in the U.S. government's policing of foreign nationals' cond...

This should terrify every person in this country. The use of machine learning systems to approximate an individuals views on war and then, if they are here lawfully on a visa, tag them for deportation is about as sci-fi dystopian as it gets.

www.axios.com/2025/03/06/s...

I remember hearing that the reason why so many so many car manufacturers started offloading like every function to touchscreens ls because it’s actually cheaper to implement than buttons and dials, while adding a “high tech” vibe.