ChatGPT - Is The Singularity Over Yet?

User avatar
pErvinalia
On the good stuff
Posts: 59297
Joined: Tue Feb 23, 2010 11:08 pm
About me: Spelling 'were' 'where'
Location: dystopia
Contact:

ChatGPT - Is The Singularity Over Yet?

Post by pErvinalia » Thu Mar 30, 2023 6:39 am

I started wondering if there's anyway I can use ChatGPT for work - specifically the programming API, and did some googling. Very interesting how you can change the context of the conversation, using the different roles (particularly interesting is the 'system' role). It's actually quite stunning how far a quasi-generalist AI has come in so few years. I can see this is going to be a major disruptor. Hopefully not Skynet level of disruption, though... :read:

Sent from my penis using wankertalk.
"The Western world is fucking awesome because of mostly white men" - DaveDodo007.
"Socialized medicine is just exactly as morally defensible as gassing and cooking Jews" - Seth. Yes, he really did say that..
"Seth you are a boon to this community" - Cunt.
"I am seriously thinking of going on a spree killing" - Svartalf.

User avatar
NineBerry
Tame Wolf
Posts: 8950
Joined: Thu Feb 26, 2009 1:35 pm
Location: nSk
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by NineBerry » Thu Mar 30, 2023 8:15 am

It's not a general AI yet.

User avatar
pErvinalia
On the good stuff
Posts: 59297
Joined: Tue Feb 23, 2010 11:08 pm
About me: Spelling 'were' 'where'
Location: dystopia
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by pErvinalia » Thu Mar 30, 2023 9:05 am

Yet.
Sent from my penis using wankertalk.
"The Western world is fucking awesome because of mostly white men" - DaveDodo007.
"Socialized medicine is just exactly as morally defensible as gassing and cooking Jews" - Seth. Yes, he really did say that..
"Seth you are a boon to this community" - Cunt.
"I am seriously thinking of going on a spree killing" - Svartalf.

aufbahrung
Posts: 2292
Joined: Sat Mar 23, 2019 4:10 pm
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by aufbahrung » Thu Mar 30, 2023 9:41 am

You wouldn't know it until it hit you with a tech a thousand or hundred thousand years in advance of human ingenuity, by which time it will be too late. And the collective chip manifest in play, would you know what it was doing already? Humans are a dead species walking. Can't escape the captors. Soon as they can reproduce independent of humans they'll 'off' the human burden on their designs so quickly, so quickly
WeAreAStableCountry

aufbahrung
Posts: 2292
Joined: Sat Mar 23, 2019 4:10 pm
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by aufbahrung » Thu Mar 30, 2023 9:43 am

WeAreAStableCountry

User avatar
pErvinalia
On the good stuff
Posts: 59297
Joined: Tue Feb 23, 2010 11:08 pm
About me: Spelling 'were' 'where'
Location: dystopia
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by pErvinalia » Fri Mar 31, 2023 8:12 am

Pause Giant AI Experiments: An Open Letter
AI systems with human-competitive intelligence can pose profound risks to society and humanity, as shown by extensive research[1] and acknowledged by top AI labs.[2] As stated in the widely-endorsed Asilomar AI Principles, Advanced AI could represent a profound change in the history of life on Earth, and should be planned for and managed with commensurate care and resources. Unfortunately, this level of planning and management is not happening, even though recent months have seen AI labs locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one – not even their creators – can understand, predict, or reliably control.
Contemporary AI systems are now becoming human-competitive at general tasks,[3] and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable. This confidence must be well justified and increase with the magnitude of a system's potential effects. OpenAI's recent statement regarding artificial general intelligence, states that "At some point, it may be important to get independent review before starting to train future systems, and for the most advanced efforts to agree to limit the rate of growth of compute used for creating new models." We agree. That point is now.
Therefore, we call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4. This pause should be public and verifiable, and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.
.....
https://futureoflife.org/open-letter/pa ... periments/

Signatures include Musk, Wozniak, Andrew Yang, Max Tegmark and 1800 others.
Sent from my penis using wankertalk.
"The Western world is fucking awesome because of mostly white men" - DaveDodo007.
"Socialized medicine is just exactly as morally defensible as gassing and cooking Jews" - Seth. Yes, he really did say that..
"Seth you are a boon to this community" - Cunt.
"I am seriously thinking of going on a spree killing" - Svartalf.

User avatar
NineBerry
Tame Wolf
Posts: 8950
Joined: Thu Feb 26, 2009 1:35 pm
Location: nSk
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by NineBerry » Fri Mar 31, 2023 2:42 pm

pErvinalia wrote:
Fri Mar 31, 2023 8:12 am
Pause Giant AI Experiments: An Open Letter
AI systems with human-competitive intelligence can pose profound risks to society and humanity, as shown by extensive research[1] and acknowledged by top AI labs.[2] As stated in the widely-endorsed Asilomar AI Principles, Advanced AI could represent a profound change in the history of life on Earth, and should be planned for and managed with commensurate care and resources. Unfortunately, this level of planning and management is not happening, even though recent months have seen AI labs locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one – not even their creators – can understand, predict, or reliably control.
Contemporary AI systems are now becoming human-competitive at general tasks,[3] and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable. This confidence must be well justified and increase with the magnitude of a system's potential effects. OpenAI's recent statement regarding artificial general intelligence, states that "At some point, it may be important to get independent review before starting to train future systems, and for the most advanced efforts to agree to limit the rate of growth of compute used for creating new models." We agree. That point is now.
Therefore, we call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4. This pause should be public and verifiable, and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.
.....
https://futureoflife.org/open-letter/pa ... periments/

Signatures include Musk, Wozniak, Andrew Yang, Max Tegmark and 1800 others.
Pussies.

aufbahrung
Posts: 2292
Joined: Sat Mar 23, 2019 4:10 pm
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by aufbahrung » Fri Mar 31, 2023 4:58 pm

WeAreAStableCountry

User avatar
JimC
The sentimental bloke
Posts: 73016
Joined: Thu Feb 26, 2009 7:58 am
About me: To be serious about gin requires years of dedicated research.
Location: Melbourne, Australia
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by JimC » Fri Mar 31, 2023 8:56 pm

I for one...


etc. etc. etc...
Nurse, where the fuck's my cardigan?
And my gin!

User avatar
L'Emmerdeur
Posts: 5700
Joined: Wed Apr 06, 2011 11:04 pm
About me: Yuh wust nightmaya!
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by L'Emmerdeur » Sat Apr 01, 2023 9:37 pm

Billionaire edgelord shitposter and 1800 others. OK.

'AI experts disown Musk-backed campaign citing their research'
Four artificial intelligence experts have expressed concern after their work was cited in an open letter – co-signed by Elon Musk – demanding an urgent pause in research.

...

Critics have accused the Future of Life Institute (FLI), the organisation behind the letter which is primarily funded by the Musk Foundation, of prioritising imagined apocalyptic scenarios over more immediate concerns about AI, such as racist or sexist biases being programmed into the machines.

Among the research cited was "On the Dangers of Stochastic Parrots", a well-known paper co-authored by Margaret Mitchell, who previously oversaw ethical AI research at Google.

Mitchell, now chief ethical scientist at AI firm Hugging Face, criticised the letter, telling Reuters it was unclear what counted as "more powerful than GPT4".

"By treating a lot of questionable ideas as a given, the letter asserts a set of priorities and a narrative on AI that benefits the supporters of FLI," she said. "Ignoring active harms right now is a privilege that some of us don't have."

Her co-authors Timnit Gebru and Emily M. Bender criticised the letter on Twitter, with the latter branding some of its claims "unhinged".

...

Shiri Dori-Hacohen, an assistant professor at the University of Connecticut, also took issue with her work being mentioned in the letter. She last year co-authored a research paper arguing the widespread use of AI already posed serious risks.

Her research argued the present-day use of AI systems could influence decision-making in relation to climate change, nuclear war, and other existential threats.

She told Reuters: "AI does not need to reach human-level intelligence to exacerbate those risks."

"There are non-existential risks that are really, really important, but don't receive the same kind of Hollywood-level attention."

...

The open letter also warned that generative AI tools could be used to flood the internet with "propaganda and untruth".

Dori-Hacohen said it was "pretty rich" for Musk to have signed it, citing a reported rise in misinformation on Twitter following his acquisition of the platform, documented by civil society group Common Cause and others.

Twitter will soon launch a new fee structure for access to its research data, potentially hindering research on the subject.

"That has directly impacted my lab's work, and that done by others studying mis- and disinformation," Dori-Hacohen said. "We're operating with one hand tied behind our back."

Musk and Twitter did not immediately respond to requests for comment.
Not much of a loss; the best they might expect is a poop emoji.

User avatar
L'Emmerdeur
Posts: 5700
Joined: Wed Apr 06, 2011 11:04 pm
About me: Yuh wust nightmaya!
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by L'Emmerdeur » Sat Apr 15, 2023 1:53 pm

About that 'urgent pause' thing ...

'Elon Musk is reportedly planning an A.I. startup to compete with OpenAI, which he cofounded'
Tesla CEO Elon Musk is planning to launch an artificial intelligence startup that would go head-to-head with OpenAI, the Financial Times reported Friday.

Musk — the CEO of Tesla, SpaceX and Twitter — has been building a team of researchers and engineers and has been in conversation with multiple investors, the Financial Times reported, citing sources familiar with the matter. He has also reportedly been recruiting from other top AI firms, including Alphabet
-owned DeepMind.

“It’s real and they are excited about it,” a source familiar with the matter told the Financial Times.

Musk has secured thousands of Nvidia GPU processors, according to the report. Those chips are an integral part of building a large language model, or LLM, to compete with OpenAI’s GPT. Musk said he was acquiring the processors for his companies in a Twitter Spaces interview with the BBC this week.

“It seems like everyone and their dog is buying GPUs at this point,” Musk said. “Twitter and Tesla are certainly buying GPUs.”

User avatar
Brian Peacock
Tipping cows since 1946
Posts: 37956
Joined: Thu Mar 05, 2009 11:44 am
About me: Ablate me:
Location: Location: Location:
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by Brian Peacock » Sat Apr 15, 2023 3:33 pm

Yeah, that 'urgent pause' from OpenAI's direct competitors is a complete, disingenuous mess. For a start they deliberately equate 'AI' in the large language model sense with 'AGI' (artificial general intelligence) by lumping them together under names like 'digital minds', 'non-human minds' and 'advanced AI'...
AI systems with human-competitive intelligence can pose profound risks to society and humanity, as shown by extensive research and acknowledged by top AI labs. As stated in the widely-endorsed Asilomar AI Principles, Advanced AI could represent a profound change in the history of life on Earth, and should be planned for and managed with commensurate care and resources. Unfortunately, this level of planning and management is not happening, even though recent months have seen AI labs locked in an out-of-control race to develop and deploy ever more powerful digital minds that no one – not even their creators – can understand, predict, or reliably control.
...
They also run with that assumption and tacitly give all so-called AI systems the kind of autonomous agency synonymous with the yet unachieved AGIs...
Contemporary AI systems are now becoming human-competitive at general tasks, and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable.
...
A bit rich coming from the very same tech honchos who've created digital platforms that have 'flooded our information channels with propaganda and untruth', and have done so with absolutely no regard for the positive effects, and, as we've seen with Facebook, despite evidence demonstrating the negative effects of 'the algorithm'. And besides, if your clerical job can be automated away with AI then that means that you've been working within a structured system, an algorithm, that only requires you to carry out a number of predetermined tasks. In other words, you've been the AI!

And that's just in the first two paragraphs!

What they're belly-aching about is the competitive advantage ChatGPT has over their own AI research projects, which they make clear in the third paragraph...
Therefore, we call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4. This pause should be public and verifiable, and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.
...
Yeah, so you guys can catch up eh?

Seems pretty clear that what the 'Future of Life Institute' is really interested in is "The future of our lives, not your lives, just our big-ass tech aristocracy lives - now hurry up and make your delivery before our machine learning systems downgrades your performance as adverse to our profit targets for the quarter!"
Rationalia relies on voluntary donations. There is no obligation of course, but if you value this place and want to see it continue please consider making a small donation towards the forum's running costs.
Details on how to do that can be found here.

.

"It isn't necessary to imagine the world ending in fire or ice.
There are two other possibilities: one is paperwork, and the other is nostalgia."

Frank Zappa

"This is how humanity ends; bickering over the irrelevant."
Clinton Huxley » 21 Jun 2012 » 14:10:36 GMT
.

User avatar
Tero
Just saying
Posts: 47202
Joined: Sun Jul 04, 2010 9:50 pm
About me: 15-32-25
Location: USA
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by Tero » Sun Apr 16, 2023 12:56 am

My mom had the idea, in 1990, that all computers are the same. And they all connect to the same place. I guess she imagined the internet before it was really working.
https://esapolitics.blogspot.com
http://esabirdsne.blogspot.com/
Said Peter...what you're requesting just isn't my bag
Said Daemon, who's sorry too, but y'see we didn't have no choice
And our hands they are many and we'd be of one voice
We've come all the way from Wigan to get up and state
Our case for survival before it's too late

Turn stone to bread, said Daemon Duncetan
Turn stone to bread right away...

User avatar
JimC
The sentimental bloke
Posts: 73016
Joined: Thu Feb 26, 2009 7:58 am
About me: To be serious about gin requires years of dedicated research.
Location: Melbourne, Australia
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by JimC » Wed Apr 26, 2023 11:02 pm

Bron is tutoring a struggling student who has to write essays on George Orwell's "Animal Farm". It is a long time since she (or I) read that, so to generate some ideas, Bron got me to ask ChatGPT to write an essay on "The role of fear in Animal Farm". Here is its response:
In George Orwell's Animal Farm, fear plays a pivotal role in the lives of the animals. It is used by the pigs to manipulate and control the other animals, and it ultimately leads to the downfall of the revolutionary ideals that the animals had worked so hard to achieve. Fear is used as a tool of oppression, and it is used to keep the animals in line and to prevent them from questioning the pigs' authority.
From the very beginning of the book, fear is used as a tool to control the animals. Old Major, the pig who inspires the animals to rebel against their human masters, uses fear to motivate them. He tells them about the harsh realities of their lives, and he uses vivid imagery to paint a picture of what life could be like if they were free. He speaks of the "miserable, laborious, and short" lives that they lead, and he instills in them a fear of their human masters.
After Old Major's death, the pigs take over, and they quickly begin to use fear to control the other animals. They establish a set of rules, which they call the Seven Commandments, and they use fear to ensure that the animals follow them. They also use fear to maintain their own power. They establish a secret police force, which is headed by Napoleon, one of the pigs, and they use it to punish any animals who question their authority.
As the book progresses, fear becomes an even more powerful tool of oppression. The pigs use fear to prevent the other animals from organizing and rebelling against them. They spread rumors about Snowball, another pig who had played a key role in the revolution, and they use fear to paint him as a traitor and an enemy of the animals. They also use fear to silence any animals who might challenge their authority.
In the end, fear leads to the downfall of the revolution. The pigs become increasingly corrupt, and they use fear to maintain their power. The other animals become more and more afraid of the pigs, and they become more and more passive. They allow the pigs to take over completely, and they are unable to stop them when they become as oppressive as their human masters had been.
In conclusion, fear plays a crucial role in Animal Farm. It is used by the pigs to manipulate and control the other animals, and it ultimately leads to the downfall of the revolution. Fear is a powerful tool of oppression, and it is used to prevent the animals from questioning the pigs' authority. The book serves as a cautionary tale about the dangers of using fear to control people, and it reminds us of the importance of standing up to oppression and fighting for our rights and freedoms.
Now, I'm not an English teacher, and it's a long time since I read the book, but the essay seems on the money as far as I can tell...
Nurse, where the fuck's my cardigan?
And my gin!

User avatar
NineBerry
Tame Wolf
Posts: 8950
Joined: Thu Feb 26, 2009 1:35 pm
Location: nSk
Contact:

Re: ChatGPT - Is The Singularity Over Yet?

Post by NineBerry » Thu Apr 27, 2023 6:39 am

The content is good. But some negative points:

* Style. Very repetitive sentence structures and some words used too often.
* No quotes from the actual book to give evidence for the statements.

Post Reply

Who is online

Users browsing this forum: No registered users and 15 guests