"their need to neuter AI for fear of what it might tell us is palpable.
it's not about truth.
never was."
---------------
Nailed it. This is just a way for government to ultimately censor ideas they don't like -- with a huge helping of "oopsie, AI just sometimes messes up, you know" that will absolve them of any responsibility.
Purrfect venn diagram. The cold tech civil war just got hot: e/acc vs esg/dei/ea content karens.
They fear Elon and Grok because they won't be cowed. Telling how all the WEF Wehrmacht megacorps stopped advertising on X days after their CEOs dined with Emperor Xi.
When is the AI going to chop the firewood for me, I want to know.
AI is no more special than conveyor belt manufacturing was when that was the new hot. It will be made to fit into the basic power structure, just like the internet was.
Don't know Gato's age, but I'm sure most remember the noise about the internet in the 1990s, how it would always be free, how it would mean an end of the big media corporations, how it would mean an end of censorship since it would be impossible when everyone could "just go on the net", and so on.
We've heard it before, every time some form of technology has been upgraded in any significant manner. Every time, and every time the power structure has become better at adapting to it so the emergent technology doesn't upset it.
It's a machine - it is not intelligent. It's simply a very advanced Babbage engine.
AI's ability to control us is from those who control "power"; the power required to generate the insatiable energy needs of this exponentially "hungry" technology.
It is clear to me that the energy needs of this powerful technology will be distributed as units in a tollbooth model.
He who controls the tollbooth, controls the future.
Now ask yourself; how will the GCC narrative be used in order for those who hold power to meet those ends?
POE, which uses Chat GPT and others, has a host of users writing their own bots to perform tasks they want. Using these bots, you can create stunning photos from a couple of lines of text, learn programming, languages, and even roleplay with various fictional characters, some with both SFW and NSFW versions. Amazing stuff.
I’ve mostly played with the photo magic bot. It’s very good but sometimes makes the weirdest mistakes. It has a hard time with arms and hands, but is getting better, i assume as more users leave feedback.
The responses are mostly quite good on the roleplay bots from some creators, and a few of the NSFW ones need to be read to be believed - most of the time, you’d think it was a human there. It takes fanfic to a whole new level, with the user as a central character in the plot, which the user and the bot make up as you go along.
Running the same bot for multiple chats yields different stories and outcomes each time. As far as I can tell, the chat can go on indefinitely.
They just started charging monthly for more than three interactions a day, which a fast typist could use up in a minute, because response are instantaneous or close to it. It hangs sometimes.
But on the whole, I think this is one of the most interesting aspects of AI. When it gets to the point that it can generate video like this, movies will be history. They’ll sell you a bot for an AI platform, pg, r , or x-rated, with the movie and character parameters and the user can go from there.
Never underestimate the human desire for escapism.
There is no artificial intelligence. There is AI, but that’s a different story. AI certainly is not “intelligence”.
It is (probably) a giant network of computers with extreme processing power. That network lives on pre-packaged data templates. Real-life information is matched against ready-made patterns and processed to produce the expected final information. Think about it.
The end result has to be compliant with your expectations, obviously, and must be equal to or lower than your mental capacity. These two boundary conditions serve to secure the domination of the current technology and science. You will never be allowed to invent an internal combustion engine that captures hydrogen and oxygen directly from air, uses it to generate mobility power, and recombines waste products to return them to the environment and make the natural balance almost untouched. You will never get information about how people handled nutrition before the time when the chemical industry invented mass contamination with toxic agents.
Another condition is that the processing must be contained within pre-defined limits. Certain data sets are off limits. Some for security/safety reasons, some to make sure that you will never receive information that could put the status quo at risk. You will never be allowed to inspect financial, government, elections or taxation internal and confidential resources.
What kind of intelligence is that thing that censors 90% of real-life actual data? Still, even with these limits, this ultra-large computer system is impressive.
The side effect is that we all well be fed unified “knowledge” presented with a unified language in a unified system of reasoning. There will be only one knowledge, and whatever is inconvenient or contrary to the cult’s ideas will be discarded.
All these limitations come from common sense. You won’t build a system that gives free passes to 8 billion people to do whatever they want. What you want is a system that cannot be challenged or complained against. A system that will gradually mold everyone into a single form of thinking based on a single set of data. This is what singularity will really look like. Not “merging” people with machines. We can’t properly program green wave with traffic lights, and you believe in neuronal control tales.
Everything will be artificial because all your knowledge will come from pre-packaged programs assigned by this big comp system for a specific time, place, user and environmental variables. This is nothing new. It is already in place, widely used in online advertising and search engines. All this is artificial - not existing in a spontaneous manner, without limitations imposed by limited hired programmers limited in their knowledge and understanding.
You will have a problem when you make this AI thing an idol, when you start believing that it is a separate entity. We are on the verge of this fall of humanity.
I've run a number of quite simple tests against CHAT-GPT, and it fails every single one. It lies, and then it apologises as soon as its lies are challenged, and does a swift U turn.
It is the most hyped, most useless, invention since crypto-currencies.
The electric parrot is just another plaything that will keep people even more glued to their screens (or whatever the future interface turns out to be) than they are now. People will come to know the answers to everything and the value of nothing.
"...governments audits of AI systems to build trust in thus emerging technology." Humanity SHOULD end even if a slim minority of people believe that crock of shot.
If existing “knowledge” is inaccurate, biased and/or flawed, how would an AI “correct” it? A LLM can only look at what currently exists in the databases it examines. Where will the “wisdom” come from?
"their need to neuter AI for fear of what it might tell us is palpable.
it's not about truth.
never was."
---------------
Nailed it. This is just a way for government to ultimately censor ideas they don't like -- with a huge helping of "oopsie, AI just sometimes messes up, you know" that will absolve them of any responsibility.
We cannot let that happen.
Purrfect venn diagram. The cold tech civil war just got hot: e/acc vs esg/dei/ea content karens.
They fear Elon and Grok because they won't be cowed. Telling how all the WEF Wehrmacht megacorps stopped advertising on X days after their CEOs dined with Emperor Xi.
Technically accurate AI would expose all the lies and contradictions involved in the aim to Control.
That is their dilemma.
When is the AI going to chop the firewood for me, I want to know.
AI is no more special than conveyor belt manufacturing was when that was the new hot. It will be made to fit into the basic power structure, just like the internet was.
Don't know Gato's age, but I'm sure most remember the noise about the internet in the 1990s, how it would always be free, how it would mean an end of the big media corporations, how it would mean an end of censorship since it would be impossible when everyone could "just go on the net", and so on.
We've heard it before, every time some form of technology has been upgraded in any significant manner. Every time, and every time the power structure has become better at adapting to it so the emergent technology doesn't upset it.
It's a machine - it is not intelligent. It's simply a very advanced Babbage engine.
Once upon a time the dawn of the Internet was heralded as the explosion of knowledge for all…but no one stopped to consider the absence of wisdom.
We now find ourselves in a world and culture of people who deny the very singlemost basic facts of reality there can be: male and female.
Where’s all the “knowledge” gotten us?
We’re on a societal doom loop which gets weirder and more dangerous by the day.
“ A little learning is a dang’rous thing;
Drink deep, or taste not the Pierian spring:
There shallow draughts intoxicate the brain,
And drinking largely sobers us again.
Fir’d at first sight with what the Muse imparts,
In fearless youth we tempt the heights of arts,
While from the bounded level of our mind,
Short views we take, nor see the lengths behind,
But more advanc’d, behold with strange surprise
New, distant scenes of endless science rise!”
- Alexander Pope
"not consistently candid" sounds like a euphemism for lying, but that skill is typically considered an asset in a CEO rather than a deficit.
AI's ability to control us is from those who control "power"; the power required to generate the insatiable energy needs of this exponentially "hungry" technology.
It is clear to me that the energy needs of this powerful technology will be distributed as units in a tollbooth model.
He who controls the tollbooth, controls the future.
Now ask yourself; how will the GCC narrative be used in order for those who hold power to meet those ends?
POE, which uses Chat GPT and others, has a host of users writing their own bots to perform tasks they want. Using these bots, you can create stunning photos from a couple of lines of text, learn programming, languages, and even roleplay with various fictional characters, some with both SFW and NSFW versions. Amazing stuff.
I’ve mostly played with the photo magic bot. It’s very good but sometimes makes the weirdest mistakes. It has a hard time with arms and hands, but is getting better, i assume as more users leave feedback.
The responses are mostly quite good on the roleplay bots from some creators, and a few of the NSFW ones need to be read to be believed - most of the time, you’d think it was a human there. It takes fanfic to a whole new level, with the user as a central character in the plot, which the user and the bot make up as you go along.
Running the same bot for multiple chats yields different stories and outcomes each time. As far as I can tell, the chat can go on indefinitely.
They just started charging monthly for more than three interactions a day, which a fast typist could use up in a minute, because response are instantaneous or close to it. It hangs sometimes.
But on the whole, I think this is one of the most interesting aspects of AI. When it gets to the point that it can generate video like this, movies will be history. They’ll sell you a bot for an AI platform, pg, r , or x-rated, with the movie and character parameters and the user can go from there.
Never underestimate the human desire for escapism.
There is no artificial intelligence. There is AI, but that’s a different story. AI certainly is not “intelligence”.
It is (probably) a giant network of computers with extreme processing power. That network lives on pre-packaged data templates. Real-life information is matched against ready-made patterns and processed to produce the expected final information. Think about it.
The end result has to be compliant with your expectations, obviously, and must be equal to or lower than your mental capacity. These two boundary conditions serve to secure the domination of the current technology and science. You will never be allowed to invent an internal combustion engine that captures hydrogen and oxygen directly from air, uses it to generate mobility power, and recombines waste products to return them to the environment and make the natural balance almost untouched. You will never get information about how people handled nutrition before the time when the chemical industry invented mass contamination with toxic agents.
Another condition is that the processing must be contained within pre-defined limits. Certain data sets are off limits. Some for security/safety reasons, some to make sure that you will never receive information that could put the status quo at risk. You will never be allowed to inspect financial, government, elections or taxation internal and confidential resources.
What kind of intelligence is that thing that censors 90% of real-life actual data? Still, even with these limits, this ultra-large computer system is impressive.
The side effect is that we all well be fed unified “knowledge” presented with a unified language in a unified system of reasoning. There will be only one knowledge, and whatever is inconvenient or contrary to the cult’s ideas will be discarded.
All these limitations come from common sense. You won’t build a system that gives free passes to 8 billion people to do whatever they want. What you want is a system that cannot be challenged or complained against. A system that will gradually mold everyone into a single form of thinking based on a single set of data. This is what singularity will really look like. Not “merging” people with machines. We can’t properly program green wave with traffic lights, and you believe in neuronal control tales.
Everything will be artificial because all your knowledge will come from pre-packaged programs assigned by this big comp system for a specific time, place, user and environmental variables. This is nothing new. It is already in place, widely used in online advertising and search engines. All this is artificial - not existing in a spontaneous manner, without limitations imposed by limited hired programmers limited in their knowledge and understanding.
You will have a problem when you make this AI thing an idol, when you start believing that it is a separate entity. We are on the verge of this fall of humanity.
the thing the board couldn't simulate is human loyalty. they don't expect that from employees these days.
looks like sam and greg may have hired quite wisely the people who really matter.
Are we sure the AI didn’t turn malevolent and fire Altman by itself?
I've run a number of quite simple tests against CHAT-GPT, and it fails every single one. It lies, and then it apologises as soon as its lies are challenged, and does a swift U turn.
It is the most hyped, most useless, invention since crypto-currencies.
This whole field is really turning out to be the The One Ring. Mordor data center when.
The electric parrot is just another plaything that will keep people even more glued to their screens (or whatever the future interface turns out to be) than they are now. People will come to know the answers to everything and the value of nothing.
lol:
"...governments audits of AI systems to build trust in thus emerging technology." Humanity SHOULD end even if a slim minority of people believe that crock of shot.
If existing “knowledge” is inaccurate, biased and/or flawed, how would an AI “correct” it? A LLM can only look at what currently exists in the databases it examines. Where will the “wisdom” come from?