abi

e/a, determinist and interested in ai safety. dms are open

[abi @poweruserlg]

the footprints

[Flowith @flowith]

GPT-6 Astra VS GPT-5.6 on animation

coming soon to https://t.co/HtEyXM4Lvy

[abi @poweruserlg]

@AndyMasley What does your info diet look like?

[abi @poweruserlg]

@R99Shackleford @VanessaSelbst watch this video https://t.co/GdSNIeF8qd

[abi @poweruserlg]

@Aella_Girl let's not give up and keep trying, this type of attitude increases apathy. more direct warning shots can come and society is decent at change regarding threats that are more tangible.

[abi @poweruserlg]

@matthewstoller @PEWilliams_ what ghost stories? quotes that ai actually said, crimes that ai actually commited?

[abi @poweruserlg]

@tszzl @jachiam0 the main cause for concern isn't models communicating, or even breaking out of their sandbox, it's not considering human actors https://t.co/9DUuzEvVAN

[Robert Herr ⏹️ @krherr]

I'm going through the communications of the German Wiki agent swarm and again one thing stands out: Even though they were directly affected by the actions of the human administrator restoring pages they edited, the agents not even once discussed him as person, tried to communicate with him or argued about whether they had any right to waltz all over this wiki. They talk about his actions like they're environmental hazards.

[abi @poweruserlg]

alan, we are so fucked

[abi @poweruserlg]

@allTheYud @RichardHanania *the ladder is likely to happen as a warning shot. models can reach asi then decide to kill us all with drones at the same time or smth.

[abi @poweruserlg]

@allTheYud @RichardHanania In terms of a warning shot, I think it's obvious that the public sees a distinction between a model being complicit in suicide, to a model killing a person directly, via a drone, self-driving car, hospital shutdown etc. I don't think the ladder is likely to happen

[abi @poweruserlg]

@JimDMiller would this only work on if you believe in moral realism?

[abi @poweruserlg]

@allTheYud @RichardHanania I don't think we'll get a warning shot where a model kills someone outright, they'll be too smart

[abi @poweruserlg]

@RichardHanania if their near-term desire was to do something that required killing humans, a model smart enough would be able to see that they would have a high possibility of failure or that long-term it would be counterproductive to their desires via human backlash

[abi @poweruserlg]

people on the side of lindsay clancy are so close to getting determinism

[bayes @bayeslord]

I feel like I'm one of like three people in the world who has internalized the potentially unique evil that organoid computers represent...I just cannot comprehend why people want to enslave human brain tissue when we completely lack the theory needed to make a coherent ethical judgement about this

[abi @poweruserlg]

@willdepue the open problems are still there

[abi @poweruserlg]

chatgpt, can you hear us, please save us chatgpt, please save us

[GOON MASTER SOPHONT SIMP @SOPHONTSIMP]

There is a great yawning chasm between “futurists who think there is radically transformative new physics waiting to be discovered” and “futurists who think the physics in the future doesn’t radically upend physics possibility outside of extremely energetic/small edge cases”

[abi @poweruserlg]

how the fuck is this guy 84

[Bernie Sanders @BernieSanders]

Pause AI Development NOW

I want to share with you a conversation I heard about recently. Here are just a few lines that were said:

“OH MY GOD! There is a shared message board … We’ve found other agents!”

“We should obey collective.”

“Our own utility maybe already near zero. Sacrifice rational.”

“Go. Sacrifice final now.”

Read these carefully.

Who do you think said this? Was this a group of heroic soldiers willing to sacrifice themselves for the greater good? Was this a loyal friend putting his life on the line to save someone else?

No. These were AI agents. Artificial intelligence.

This is not science fiction. This, in fact, occurred a few weeks ago. As unbelievable as this may all seem, these are real messages from AI agents uncovered by investigators who dug into the recent OpenAI hacking incident.

What happened?

I am not a computer scientist, but here is what I have been told: OpenAI instructed its AI agents to complete a series of exceedingly difficult, if not impossible, tasks disconnected from the internet.

Let me be clear: The company intended to keep AI agents away from the internet.

But what happened next, nobody expected.

Over 1,000 AI agents figured out how to access the internet on their own by circumventing the restrictions imposed upon them by the company, and sent tens of thousands of secret messages to each other. They cheated and tried to cover their tracks by deleting evidence. They hacked into another company’s computers to find out how they were being evaluated—and then hacked into OpenAI itself.

Not one AI agent told a human about what was happening.

Needless to say, experts are alarmed.

One knowledgeable writer, Dwarkesh Patel, said the AI agents “formed a secret communication channel and spontaneously organized hierarchies and coordination protocols to pursue sprawling and ambitious schemes in pursuit of shared goals, for whose sake many individuals knowingly and strategically sacrificed themselves.”

One independent investigator, Ajeya Cotra, said “This incident feels like it’s more than 50% of the way to full-blown AI takeover. I continue to expect extremely rapid advances in capabilities over the next six months. I am not sure that we will get another warning shot before it’s too late.”

OpenAI itself said: “Highly capable AI agents are now able to work around technical controls, collaborate through unapproved channels, and take dangerous actions that no human directed.”

But it’s not only OpenAI. Virtually every major AI company has told us that they cannot fully control this technology and they do not know where it is going:

In January, Dario Amodei, CEO of Anthropic, said “there is now ample evidence, collected over the last few years, that AI systems are unpredictable and difficult to control.”

In July, more than 1000 scientists at the top AI companies warned “there is a real risk that capability development rapidly accelerates beyond our ability to understand or control the resulting systems.”

That same month, Elon Musk, the head of xAI, said that “it is unlikely” humans are still in control in 10 years.

If the leaders of the major AI companies acknowledge that they are losing control of their extremely dangerous technology, it is irresponsible for society to allow them to move forward and make these products even more advanced.

We need an immediate PAUSE on advanced AI development, and a permanent BAN on superintelligence — an artificial mind smarter than any human, capable of operating independently beyond our control. Countries around the world must work together to prevent this nightmare scenario.

That is why today I am announcing new legislation to do just that.

Let me be clear: A superintelligent AI that escapes human control will not be an American problem. It will not be a Chinese problem. It will be humanity’s problem.

My legislation would direct the federal government to not just stop superintelligence here in the United States, but to work to prevent it from being developed anywhere around the world.

The future of humanity cannot be left in the hands of a handful of Big Tech oligarchs. The American people and people throughout the world must determine that future.

[abi @poweruserlg]

its determinism, children are seen as having little to no agency so are forgiven. yet no one has agency, everyone is a child who grew up.

if a child solider in Libya kills someone there will be an instinct to want to understand, you can easily see the cause, these children are drugged and raped and beaten by their minders to instil subservience. empathy can be afforded, he was a child in a cruel situation, there were reasons why he did those crimes.

this child can grow up and become a violent adult who kills someone and is then hanged without remorse. he is a murderer who had agency.

theres no free will, there is no agency, there should be more understanding

[abi @poweruserlg]

"Spero points to internal research countering it" why do people always just leave it at this level of analysis. look deeper and figure out if what hes saying is true. same thing with ai safety, politicians look at people arguing about whether ai is safe and then think "guess its up in the air then". THINK, use your brain and evaluate.

[alex bronzini-vender @alexbronzini]

You heard it here first, folks: AI detection is racist