• We have updated the guidelines regarding posting political content: please see the stickied thread on Website Issues.
Elon Musk and other tech experts call for a ‘pause’ on advanced AI systems

Over 1,000 executives and researchers have signed an open letter calling for a halt to what they have called a ‘dangerous’ arms race. The letter states: "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... We call on all AI labs to immediately pause for at least six 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.” The issue of this letter follows the release of powerful AI tools such as GPT-4.

Source - Financial Times link: https://www.ft.com/content/3f584019-7c51-4c9c-b18f-0e0ac0821bf7

Any thoughts on this?
 
Last edited:
Elon Musk also makes cars with self-driving AI that many critics believe is dangerous to the safety of the highways.
Discuss.
It should be safer than with human drivers, but it's not.
More development and testing required.
 
Elon Musk also makes cars with self-driving AI that many critics believe is dangerous to the safety of the highways.
Discuss.

This is what made me raise my eyebrows too. They may be completely right about the dangers surrounding AI, but I also wonder whether there are some corporate motivations involved too (fear they don't get a sizable slice of the lucrative pie, or otherwise lose their grip on it).
 
These Jay Z verse is in fact written by AI.

Causing a debate about copyright, and control of creativity.

And if this software is in the public domain, what might be lurking behind closed doors?
 
I do think that humans will become over-reliant on their mobile phones and the use of AI.
It will lead to de-skilling, hesitancy in decision-making, a smaller human knowledge base and lower IQs.
Ultimately, human evolution may go into reverse and civilisation may begin to crumble (we are seeing signs of this now),

I urge everyone to watch the film 'Idiocracy'.
 
I urge everyone to watch the film 'Idiocracy'.
I do too.
It's far from a 'great' film, but it is good, with many, many things depicted that were seen as ridiculous impossibilities at the time, but many of which are slowly becoming more and more relevant.
 
I do too.
It's far from a 'great' film, but it is good, with many, many things depicted that were seen as ridiculous impossibilities at the time, but many of which are slowly becoming more and more relevant.
idiocracy 1.gif
 
Now ChatGPT is defaming people.

An Australian mayor said he may take legal action over false information shared by advanced chatbot ChatGPT.

Brian Hood, Mayor of Hepburn Shire Council, says the OpenAI-owned tool falsely claimed he was imprisoned for bribery while working for a subsidiary of Australia's national bank. In fact, Mr Hood was a whistleblower and was never charged with a crime.

His lawyers have sent a concerns notice to OpenAI - the first formal step in defamation action in Australia. OpenAI has 28 days to respond to the concerns notice, after which time Mr Hood would be able to take the company to court under Australian law. If he pursues the legal claim, it would be the first time OpenAI has publicly faced a defamation suit over the content created by ChatGPT.

OpenAI has not responded to a BBC request for comment. ...

The BBC was able to confirm Mr Hood's claims by asking the publicly available version of ChatGPT on OpenAI's website about the role he had in the Securency scandal. It responded with a description of the case, then inaccurately stated that he "pleaded guilty to one count of bribery in 2012 and was sentenced to four years in prison".

But the same result does not appear in the newer version of ChatGPT which is integrated into Microsoft's Bing search engine. It correctly identifies him as a whistleblower, and specifically says he "was not involved in the payment of bribes... as claimed by an AI chatbot called ChatGPT".

https://www.mirror.co.uk/news/us-news/haunted-hotel-people-scratched-bitten-29654504
 
I asked GTP-4 to do something important, tell me how we should solve world hunger.
------------------------------

Me:
How do we solve world hunger?
-
ChatGPT:
Solving world hunger is a complex and multifaceted issue that requires a combination of strategies at various levels. Some of the steps that could be taken include:
  1. Increasing agricultural productivity: Efforts should be made to increase the productivity of small-scale farmers who form the majority of the world's poor and who rely on agriculture for their livelihoods. This could involve providing access to better seeds, fertilizers, and irrigation, as well as training and education on sustainable farming practices.
  2. Improving access to food: Efforts should be made to improve access to food for the most vulnerable populations, such as children, pregnant and breastfeeding women, and the elderly. This could involve implementing food aid programs, providing cash transfers, or creating safety nets to help people cope with shocks such as droughts or economic crises.
  3. Reducing food waste: One-third of all food produced for human consumption is lost or wasted, which is a significant contributor to world hunger. Efforts should be made to reduce food waste by improving storage and transportation infrastructure, promoting better food distribution systems, and educating consumers about the value of food.
  4. Addressing poverty: Poverty is a root cause of hunger, and efforts should be made to address poverty through job creation, access to education, and social protection programs.
  5. Addressing conflict and instability: Conflict and instability can lead to food insecurity by disrupting food systems, causing displacement, and limiting access to food. Efforts should be made to address the root causes of conflict and promote peace and stability.
Overall, addressing world hunger will require a comprehensive approach that addresses the underlying causes of food insecurity and involves the collaboration of governments, civil society, and the private sector.
 
What about reducing world population?
That was not mentioned. Perhaps because it's part of conspiracy theories.

Try it yourself. It's possible to register and use it for free.
 
I haven't yet seen it, but I urge everyone to read C.M. Kornbluth's story "The Marching Morons", which has a similar plot. I really think we're heading that way.
I seem to recall reading that back in the early 80s.
Idiocracy does owe some of its ideas to that story.
 
I urge everyone to watch the film 'Idiocracy'.
Idiocracy does seem to have accurately depicted the drift in popular culture towards 'echo chambers' and unsupported conspiracy theories. On the other hand, the trend in the general population seems to be towards increasing intelligence, rather than a decrease; if we only consider the measured IQ of the population, the 'average' (which is always set at 100) has had to be adjusted upwards several times over the last fifty years.

This is known as the Flynn Effect, and may be due to the increasing familiarity that the general population has with the testing procedures.
https://en.wikipedia.org/wiki/Flynn_effect

...and there are some indications that this effect has decreased or even reversed in recent years.
In the United Kingdom, a study by Flynn (2009) found that tests carried out in 1980 and again in 2008 show that the IQ score of an average 14-year-old dropped by more than two points over the period. For the upper half of the results, the performance was even worse. Average IQ scores declined by six points.
 
Idiocracy does seem to have accurately depicted the drift in popular culture towards 'echo chambers' and unsupported conspiracy theories. On the other hand, the trend in the general population seems to be towards increasing intelligence, rather than a decrease; if we only consider the measured IQ of the population, the 'average' (which is always set at 100) has had to be adjusted upwards several times over the last fifty years.

This is known as the Flynn Effect, and may be due to the increasing familiarity that the general population has with the testing procedures.
https://en.wikipedia.org/wiki/Flynn_effect

...and there are some indications that this effect has decreased or even reversed in recent years.
Yes... people seem to have become better at doing tests and exams. This does not mean that they are smarter.
 
Yes... people seem to have become better at doing tests and exams. This does not mean that they are smarter.
Quite. It is not possible to compare the intelligence of a population in the past with one in the present without allowing for the fact that people nowadays are trained to answer IQ-type questions. We actually think differently nowadays. Try answering some of Lewis Carroll's conundrums from the 1860s; they use completely different language and assumptions.

I wonder how Carroll might have coped with Python.
 
Quite. It is not possible to compare the intelligence of a population in the past with one in the present without allowing for the fact that people nowadays are trained to answer IQ-type questions. We actually think differently nowadays. Try answering some of Lewis Carroll's conundrums from the 1860s; they use completely different language and assumptions.

I wonder how Carroll might have coped with Python.
Maybe, in order to be able to move forwards we have to accept to take some steps backwards and ditch the heavy outdated luggage?
 
Now ChatGPT is defaming people.

An Australian mayor said he may take legal action over false information shared by advanced chatbot ChatGPT.

Brian Hood, Mayor of Hepburn Shire Council, says the OpenAI-owned tool falsely claimed he was imprisoned for bribery while working for a subsidiary of Australia's national bank. In fact, Mr Hood was a whistleblower and was never charged with a crime.

His lawyers have sent a concerns notice to OpenAI - the first formal step in defamation action in Australia. OpenAI has 28 days to respond to the concerns notice, after which time Mr Hood would be able to take the company to court under Australian law. If he pursues the legal claim, it would be the first time OpenAI has publicly faced a defamation suit over the content created by ChatGPT.

OpenAI has not responded to a BBC request for comment. ...

The BBC was able to confirm Mr Hood's claims by asking the publicly available version of ChatGPT on OpenAI's website about the role he had in the Securency scandal. It responded with a description of the case, then inaccurately stated that he "pleaded guilty to one count of bribery in 2012 and was sentenced to four years in prison".

But the same result does not appear in the newer version of ChatGPT which is integrated into Microsoft's Bing search engine. It correctly identifies him as a whistleblower, and specifically says he "was not involved in the payment of bribes... as claimed by an AI chatbot called ChatGPT".

https://www.mirror.co.uk/news/us-news/haunted-hotel-people-scratched-bitten-29654504
I regularly see arguments that chatgpt isnt "ai" because it will get things wrong. But humans get things wrong too, and we are considered intelligent.
 
I regularly see arguments that chatgpt isnt "ai" because it will get things wrong. But humans get things wrong too, and we are considered intelligent.
It's also worth mentioning that there are many cases whereby getting things wrong, lead to gaining further intelligence, and therefore furthering more knowledge!
 
Back
Top