Earlier quoted context omitted.
Murder
Why did the murder happen?
Because someone wanted someone else's stuff.
An Alien Mind
471–480 of 490 posts
Re: An Alien Mind
#472Earlier quoted context omitted.
This explains nothing. Money buys a lot of power, and he could have easily just had both.
Nah, money doesn’t buy ALL power. Only power of a certain kind (read ownership of a system that many rely on) can’t be bought.
Again, this misses the point. Why did he turn down an equity stake that likely would have been worth hundreds of billions? It's not like it would have jeopardized the power you're talking about.
Re: An Alien Mind
#473Earlier quoted context omitted.
Nah, money doesn’t buy ALL power. Only power of a certain kind (read ownership of a system that many rely on) can’t be bought.
Again, this misses the point. Why did he turn down an equity stake that likely would have been worth hundreds of billions? It's not like it would have jeopardized the power you're talking about.
If anything that proves the point. The power wasn’t in the money (which he already had plenty of, as you say).
Re: An Alien Mind
#474Surprised that there is no discussion on the technical aspects of TFA. Specifically, the emphasis on CoT monitoring that does not even mention the fact that models' CoT traces do not necessarily correspond to the internal "latent space" of "weight space" reasoning they used to arrive at a response. (Look up "Chain of Thought faithfullness.")
That simultaneously seems like truly alien behavior... yet is also strikingly similar to how science suggests humans think! (Look up confabulation / choice blindness / ex-post rationalization.) It's truly a huge WTF to consider that LLMs somehow have emergently developed an analogous reasoning mechanism purely through training on our knowledge artifacts. Is this due to something encoded in the data, or an emergent property of all intelligences, or entirely unrelated phenomena in humans and LLMs?
But WTF's aside, to me that discrepancy seems to be the biggest risk of all. How can we monitor anything if the metric we are looking at itself is unreliable? I suppose we would need to monitor latent space reasoning but I suspect that is prohibitively expensive and very rudimentary and I have seen no claim that it is feasible.
So are we even really monitoring the right thing to measure alignment? Or is OpenAI just throwing this out there as a demonstration that they're "doing something" about this?
Re: An Alien Mind
#475> Three years later, reasoning language models are a rapidly growing part of the economy
“We really hope this is true - our bottom line is dependent on it. If we keep saying fairies exist maybe they will”
Re: An Alien Mind
#476openai is deflecting. this blog post of theirs is just another dopamine hit to distract logical minds with 'greater concerns' so they can keep building their machine. it's not enough they are displacing humans from work, consuming increasing amounts of electrical power so humans have to pay more for it, creating disinformation bubbles with avalanches of slop. they dont care about alignment - these words are theater -…
Agreed, alignment is an inside joke. The fact that they admit that it's done by... AI is quite revealing. About the job losses however, either that tech isn't as useful as it's hyped to be, or it's so useful that it's creating new jobs. Just saw this: https://www.newyorker.com/news/the-financial-page/has-the-ai...
Re: An Alien Mind
#477Earlier quoted context omitted.
What did fizzle away then and why do you believe AI is more similar to that thing than to computers?
Lots of goddamn awesome computers fizzled out. The Amiga being a prime example. Besides you can't just wave your arms in the most vague terms and then deny that survivor bias was ever a thing.
So your argument is that AI is more lika Amiga than computers? I'd say that Amiga wouldn't fizzle out if it wasn't superceded by pc. It very well may be that transformer architecture is going to be superceded by something like jepa or other world models but it doesn't change much.
Survivor bias is always a thing but it's not everything. All surviving things are not equal and neither are all gone things. If there are such things. Some cls technology never dies. There are new games written for 8-bit Atari today.
Re: An Alien Mind
#478Earlier quoted context omitted.
Eh… No. I get the appeal, but lying is a sub-category of deception, and deception itself is a child of error. Meaning deception is inherently something that the physics of reality allows. In the most simplistic sense, the camouflage of moths that look like snakes, or a chameleon’s ability to change colour, is deception. In that sense, deception is the ability to fool the sensors of a specific category of targets. It…
It is critical for things like revolutions to occur, but I don't see a reason to believe that revolutions would be necessary in the world that I am describing. Revolutions are necessary when the majority is not being represented, but in an honest world, those collectives would not be elected to begin with. In an honest world, they wouldn't be able to clutch onto power by misdirecting and deceiving the public, and lyi…
You are focusing on deception as a category of malice and intentional behavior.
For arguments sake, let’s assume two people watch an event and found religions based on their perception of it.
This is purely a matter of belief, based on what they saw. No one is lying in this situation, they just perceived different things.
This seems like a fantastic extrapolation from your premise, but the degree of change you are arguing for will reach exactly this point, multiple times throughout history.
Fundamentally, you are arguing for a different physical reality than the one you inhabit.
Re: An Alien Mind
#479Earlier quoted context omitted.
But that was kind of my point Maybe it'd be easier to train the models on key parts of the legal code and give it a hard aversion to breaking the law - rather than training on vague value judgements and then hope the model doesn't break the law
I got that. I'm saying that it is deliberate. Wiggle room et all.
How does not explicitly trying to train the model specifically not to break the law give them any wiggle room if the model then goes and breaks the law?
Re: An Alien Mind
#480One of my favorite things to do with these blog posts is to imagine an Alien Museum on the Remains of Humanity, and wonder what the little text flyouts and commentary on the screenshot of this one might say. Some ideas: "Despite a nuanced view of the complexities of what lay ahead, humanity found itself collectively unable to stop the process it had set in motion." "Despite significant progress on the mechanisms of a…
[flagged]