I’m not sure how fair dinkum this is.
Maybe some of the more technical of us can verify it, but if it’s true you can understand the concerns of folks like scriptwriters, actors and musicians over the impact of AI on their intellectual property.
There’s often a debate over the best lead singer of some of the big power ballad groups of the 70s and 80s.
Often the popular choice is Freddie Mercury.
My personal favourite is Steve Perry of Journey.
Has AI made it possible for a more direct comparison.
The Mercury clip is still a little ‘tinny’ but time will only improve the quality as the technology improves.
https://www.youtube.com/watch?v=VcjzHMhBtf0
https://www.youtube.com/watch?v=SbZlQcys6o0
I asked the AI should we go after Clayton Oliver :D :D :D
They're not sure.
According to recent news, Melbourne is open to trading their star midfielder, Clayton Oliver, with rival clubs already enquiring about his availability 12. However, Melbourne is not willing to part ways with the 26-year-old unless they get the right deal in return 1. Oliver is a four-time best and fairest winner at the Demons and is contracted until the end of 2030 on a lucrative contract 3.
It’s unclear whether Carlton has expressed interest in acquiring Oliver. However, given his impressive track record and the fact that he is still young, it’s possible that Carlton might consider acquiring him if they believe he would be a good fit for their team.
It’s worth noting that Oliver endured a difficult 2023 campaign, primarily due to consistent injury setbacks that cost him half the season 4. He was also out of action from Rounds 14 to 19 and was forced to address ugly drug rumors that spread like wildfire on social media 5. However, despite these setbacks, Oliver remains one of the most talented midfielders in the league and would be a valuable asset to any team that acquires him.
In summary, while it’s unclear whether Carlton should acquire Clayton Oliver, it’s worth considering his impressive track record and potential value to the team.
Same page here, Principal LODS.
Steve Perry is by far my favourite pop/rock vocalist. He and Ann Wilson (Heart) are both extraordinary and standout vocalists from that era... well, any era really.
Agree that Freddie's AI version of this classic song is 'thin' in comparison to Steve. But scary none-the-less where AI may go with imitating vocalists.
I'm not sure you need to worry about the artistic stuff as much as you should worry about the political.
I was at a conference a couple of years back, and Adobe demonstrated software that allowed you to write a speech and have it read in the voice of your preferred presenter, the example they used was Obama presenting a speech asserting the Republican conspiracy theories were correct. Now that software has been extended in capability to include video, you can have the voice and the video of the person making the speech and the lips and face movements are almost indistinguishable from real. All you have to do is link to pre-existing videos of the presenter for the software to learn from, and it will make a fake using your text, it will even correct your text so the grammar fits the speech pattern of the presenter.
Trump supporters got right onto this early and start posting fakes of Obama, Biden and Clinton like running water, but Google and Facebook put measures in place to quickly curtail the activity.
Year 5/6 kids at my sons primary school where he works using ChatGpt to complete essays, creates more work for the teachers having to go on these sites and pull up answers and compare them with the students work.
We are all in a simulated reality anyway. So its just a simulation simulating another simulation.
They can all sing.
Do this with Steve Perry singing Queen's Don't Stop Me now then see what the result is.
It is hard to compare as they will generally sing songs that sit in their 'pocket' that bring the best out of their tone and range.
Steve Perry has a higher voice than Freddie, so Don't Stop Believing may suit Perry more.
Who's the best? Doesn't really matter. It's whatever floats your boat.
I have seen a clip of We Are The Champions with the vocals isolated - it's pretty cool and hard to fault.
Don't Stop Believing with Vocals isolated
https://www.youtube.com/watch?v=kkEJZp6Zwn4 (https://www.youtube.com/watch?v=kkEJZp6Zwn4)
Don't Stop Me Now with Vocals isolated
https://www.youtube.com/watch?v=1Q_e03bd5lw (https://www.youtube.com/watch?v=1Q_e03bd5lw)
Not songs that we should attempt at Karaoke.
Yep
It wasn't really meant as a 'one's better than the other, both are tremendous power singers...and it's a personal preference.
It was more about the technology.
I'm still not certain where I stand.
It would be great to hear singers of the past doing songs they didn't record while alive.
But there may be ethical issues that need addressing.
Who benefits financially from the singers 'intellectual property'?
The singer has no control over the music...he may have been very resistant to recording a particular song or genre?
Old band members can 'reform' with the deceased on AI, not necessarily a bad thing.
I understand Lennon's voice has been AI'd to some old Beatles material
But do we want a top 40 consisting of Buddy Holly, Elvis, Jim Morrison, Jimi Hendrix, Janis Joplin, Bowie etc singing new material
(I reckon 80%+ will answer yes) ;) :D
Implications are also there for actors as the technology advances.
Will we see Marylin Monroe in "Barbie 2"
or
Oppenheimer himself in "Oppenheimer 2"
It's a brave new world :-\
Still gotta give it to Freddie
Yep
It wasn't really meant as a 'one's better than the other, both are tremendous power singers...and it's a personal preference.
It was more about the technology.
I'm still not certain where I stand.
It would be great to hear singers of the past doing songs they didn't record while alive.
But there may be ethical issues that need addressing.
Who benefits financially from the singers 'intellectual property'?
The singer has no control over the music...he may have been very resistant to recording a particular song or genre?
Old band members can 'reform' with the deceased on AI, not necessarily a bad thing.
I understand Lennon's voice has been AI'd to some old Beatles material
But do we want a top 40 consisting of Buddy Holly, Elvis, Jim Morrison, Jimi Hendrix, Janis Joplin, Bowie etc singing new material
(I reckon 80%+ will answer yes) ;) :D
Implications are also there for actors as the technology advances.
Will we see Marylin Monroe in "Barbie 2"
or
Oppenheimer himself in "Oppenheimer 2"
It's a brave new world :-\
Not sure if you are aware but SAG (screen actors guild) are striking at the moment basically for this reason.
The actors can pretty much be made obsolete with basically current technology. We could have new Brad Pitt movies coming out for the next 300 years.
Not sure if you are aware but SAG (screen actors guild) are striking at the moment basically for this reason.
The actors can pretty much be made obsolete with basically current technology. We could have new Brad Pitt movies coming out for the next 300 years.
Yep, very aware.
The Screenwriters are back.
The actors are still negotiating...not just about AI but also there are issues around streaming and the revenue they used to get from re-runs of shows
I just get the feeling that it's all pretty much swimming against a Tsunami.
The genie is out of the bottle.
Yep
It wasn't really meant as a 'one's better than the other, both are tremendous power singers...and it's a personal preference.
It was more about the technology.
I know Lods, but couldn't help myself, sorry! But it's pretty cool to hear the clear diction and both were note perfect. (as well as the rest of the Queen and their harmonies).
What will be scary is when scammers hack your phone, get a recording of your voice voice, send a text/message showing your number, but using a different one, use your voice, ask for money from a rellie and then it gets sent to a 'wrong' account.
Three top international crimes are:
Weapons
People Trafficking
Drugs
Surely scamming/cyber crime has to be number 4 with a bullet.
ChatGpt had Freddie Mercury, Bruce Springsteen, Prince and Bono as the best male lead singers of a band in that 80's era when I asked the question....Steve Perry didnt get a mention.
ChatGpt had Freddie Mercury, Bruce Springsteen, Prince and Bono as the best male lead singers of a band in that 80's era when I asked the question....Steve Perry didnt get a mention.
Lets ask Brian May. :D
https://societyofrock.com/what-makes-steve-perry-such-a-great-singer/#:~:text=Perry%20has%20an%20incredibly%20powerful%20range%20%E2%80%93%20spanning,has%20a%20smooth%20tone%20and%20a%20perfect%20pitch.
Perry has an incredibly powerful range – spanning from F#2 to A5. As far as singing goes, he’s peerless and a force of nature at that. Even fellow rockers have nothing but praises for him. Queen’s Brian May even described him as “a truly luminous singer” and “a voice in a million.” Plus, he has a smooth tone and a perfect pitch. He essentially raised the bar for every other lead singer out there with his emotive delivery which gave an extra punch to Journey’s power ballads.
Perry's my favourite.
Others would have a different choice.
You'd get a fair few in front of the AI choices (apart from Mercury) from most people.
I like Springsteen...but you need subtitles. :D :D
ChatGpt had Freddie Mercury, Bruce Springsteen, Prince and Bono as the best male lead singers of a band in that 80's era when I asked the question....Steve Perry didnt get a mention.
Here's what I got when I asked the AI who were the best power ballad singers of the 1980s
The 1980s was a decade of power ballads, and many male singers made their mark in this genre. Some of the best male power ballad singers of the 1980s include:
Michael Bolton: Michael Bolton is an American singer and songwriter who rose to fame in the 1980s. He is known for his powerful voice and emotional ballads. Some of his most popular power ballads from this decade include “How Am I Supposed to Live Without You” and “When a Man Loves a Woman” 1.
Richard Marx: Richard Marx is an American singer, songwriter, and producer who had several hits in the 1980s. Some of his most popular power ballads from this decade include “Right Here Waiting” and “Hold On to the Nights” 2.
Steve Perry: Steve Perry is an American singer and songwriter who was the lead vocalist of the rock band Journey. He had several hits in the power ballad genre, including “Open Arms” and “Faithfully” 3.
Bon Jovi: Bon Jovi is an American rock band that had several hits in the 1980s, including “Livin’ on a Prayer” and “Wanted Dead or Alive.” The band’s lead singer, Jon Bon Jovi, is known for his powerful vocals and emotional performances 4.
Foreigner: Foreigner is a British-American rock band that had several hits in the 1980s, including “I Want to Know What Love Is” and “Waiting for a Girl Like You.” The band’s lead singer, Lou Gramm, is known for his powerful voice and emotional performances 5.
These are just a few examples of some of the best male power ballad singers from the 1980s. There were many other talented artists who made their mark in this genre during this decade.
Here's what I got when I asked the AI who were the best power ballad singers of the 1980s
Scary😳
I'll throw in Paul Rodgers of "Free and Bad Company fame" as my No 1.
Queen chose him to work with as well and I thought he was very good at filling in for Freddie when Queen toured for a few years.
These LLM AIs can be manipulated by starting a counter-argument, you can basically debate with the engine and it will change the response to make you happy with the answer, truth and accuracy mean very little.
Also careful crafting of any question will change the response as the LLM take a very literal interpretation of the question, so much so drafting questions is now a career option for some segments of business!
Ask the same fundamental question worded two different ways, and get different answers.
As much as people fear AI, I suppose it is natural to fear something you do not understand or cannot observe, when you see what is going on right now surrounding Russia, Ukraine, Israel, Palestine and some TBA, you basically have the likes of Trump, Zuckerberg and Musk to thank for much of this.
They are easily observed, and you are far better off fearing them than an AI, vaccine or referendum!
They profit from various roles and enterprises by fostering doubt, casting aspersions and dividing society, and unlike an AI which acts mechanically without consciousness, these people do it deliberately.
Seriously, it's like the French Revolution never happened in Meta's version of history!
AI should very much be feared. Its just a matter of when.....and its most likely not now.....and may not be for a long time.
The neural networking stuff is where things get weird. The AI teaches itself, and we don't know how it is actually doing it.
Its a black box.
We give it inputs, and we look at the outputs and tell it if its right or wrong and it adjusts itself as required.
It is already better at looking for diseases in x-rays than the best trained doctors.....and we dont know what it is seeing that we cannot.
I've mentioned it before, but look up "The end of the world with Josh Clark" podcast. It has an episode dedicated to AI and explains things a lot better than i could.
There was a part in it about how we need to be very careful with what we tell AI as it could very much end us by accident without the right fail safes involved.
It has an example. A paper clip company uses AI to become more efficient. Initially AI creates efficiency in production line, packaging etc. It looks at getting better materials to get the best quality paper clips. It can build machines to do this. It grows and grows and wants to maximise resources, be that land for mining, water for production. Eventually realises that humans are simply getting in the way and wipes us out as well to 'loot' our 'resources' to make better paper clips. It creates space ships to go mine asteroids for better materials etc etc.
Its a ludicrous scenario, and i've left out a lot of detail, but step by step, each next step is plausible and possible in the not too distant future.
I mean Kubrick was predicting this kind of (humans getting in the way) over 50 years ago with HAL in 2001.
"I'm sorry Dave, i'm afraid i can't do that"
It might not happen until long after we are all dead and buried...but it might happen sooner.
Moore's law makes it hard to comprehend how quickly and how advanced the future will be.
Throw in some quantum computing and anything is possible.
Whatever it takes?
The fears over AI are greatly exaggerated, it's basically software, and currently it requires a high bandwidth 24x7 power intensive connection to the web to work, and because the web is full of shizen AI gets about 40% of it's answers wrong.
The AI we are exposed to like ChatGPT or OpenAI pretty much requires a server farm the size of the MCG to deliver 40% wrong answers in the timeframe people expect from a Google search.
The real problem is dumb-ar5e people believing the AI is always right without question, or nefarious types find ways to us AI to manipulate or con others. Either way the problem is people, not a hunk of silicon or a few lines of code.
Finally, the best of the best technology fails with even rudimentary human intervention. For example AI Drones can fall out of the sky or run into buildings just from someone turning the lights on or off, because machine vision isn't all it's cracked up to be, and it's not really intelligent in the way a person knows all trees are trees just from seeing just one up close.
Im skeptical about AI, because ultimatey, machines don't learn without good data being fed to it.
Anyone who has ever had to look at a web application firewall can see that they are bloody hopeless and start blocking legitimate traffic for stupid reasons.
You guys are talking about AI as it currently exists.
I'm talking about AI in the future, how far into the future is anybodys guess and its almost impossible to fathom.
Just like 100 years ago, it was impossible to fathom a contraption that could be used as a calculator doing basic mathematical operation any pre-schooler can do. When it eventually came to be, it was as big as a room. Now everyone carries that, and 100 other inventions capable of so much more, in their pocket.
What does 100 years from now look like??
30 years ago the thought of self driving cars was nothing more than sci fi nonsense. Now it exists.
Chat GPT is like the first fish that every crawled out of the water and onto land.
AI i'm talking about is humans taking over the planet.
There are a lot of steps from then to now, but it will happen. Time being the only unknown.
I think we must terminate this debate, where is
@madbluboy when you need him?
I think the idea of an all seeing all conquering Cognisant AI is greatly overstated, and if we create something with such a high level of intelligence then it's unlikely to unilaterally turn on it's creator. Not all AI if it ever exists is going to become Norman Bates!
We can imagine a lot of stuff, most of it will never be real!
A bigger issue is poor quality robotic automation, and a lot of what the media refers to as AI is mostly robotic automation, and it's not intelligent in any way! Intelligent in it's design but not encompassing intelligence.
Pretty soon Windows 11 users will be fully exposed to MS CoPilot and other similar "apparently smart" technologies, but they are just forms of robotic automation based on LLM and not AI at all! LLM is basically the data on the internet reduced to a library of relationships that can be searched for an answer, it's not that smart and most of the answers it will send right or wrong are parroted replies originally authored by humans before being repeated or rehashed by the LLM robotics. None of it can pass a Turing Test. It's rote learning on a massive scale, not understanding.
I think we must terminate this debate, where is @madbluboy when you need him?
I think the idea of an all seeing all conquering Cognisant AI is greatly overstated, and if we create something with such a high level of intelligence then it's unlikely to unilaterally turn on it's creator. Not all AI if it ever exists is going to become Norman Bates!
We can imagine a lot of stuff, most of it will never be real!
A bigger issue is poor quality robotic automation, and a lot of what the media refers to as AI is mostly robotic automation, and it's not intelligent in any way! Intelligent in it's design but not encompassing intelligence.
Pretty soon Windows 11 users will be fully exposed to MS CoPilot and other similar "apparently smart" technologies, but they are just forms of robotic automation based on LLM and not AI at all! LLM is basically the data on the internet reduced to a library of relationships that can be searched for an answer, it's not that smart and most of the answers it will send right or wrong are parroted replies originally authored by humans before being repeated or rehashed by the LLM robotics. None of it can pass a Turing Test. It's rote learning on a massive scale, not understanding.
Mate, you are still thinking 5 minutes down the road. You need to think decades into the future.
We are a lot closer than you think.
All it will take is some crazy Elon Musk style billionaire to go rogue and things get pretty tricky pretty quickly.
Nano-bots can do many weird and wonderful things and are expected to be a big player in our lifetime.
AI is already streets ahead of us in terms of some kinds of diagnoses.
Put the 2 together and we have AI finding issues and fixing us (for a small fee of course) in the not too distant future.
"The first ultraintelligent machine, is the last thing man will ever need to make."Once this is achieved, it can design and improve upon itself quicker than we can keep up and its about then that we are just along for the ride.
We can already see some of this stuff occuring in our lifetimes.
The movie hidden figures about the african american women who were doing the calculations for NASA back in the day....us as humans, couldn't do the same thing now because we use computers to do it for us.
Logarithm slide rules etc, that had all come and gone before my time. Thats a computer thing now.
The better computers get at this stuff, the less we need to know it. Humanity, is largely getting dumber thanks to our current technologies.
We already have social media sites reading our minds and predicting our wants and needs as well as feeding us (mis)information changing how we vote without us even realising it.
As i mentioned earlier, our cars are starting to drive themselves, and it won't be long before we don't know how to drive ourselves.
The more technology does for us, the less we can do it for ourselves.
Soon that same technology will be better at everything we can do for ourselves.
Some of the smartest people in the world, Hawking, Musk etc can see this as a potentially catastrophic threat, and i certainly don't see any reason to not agree with them.
Again, its just a matter of when....not if.
Individually, we may be long gone before we even get close.
If I'm not...I'll be on their side. :D :D
If I'm not...I'll be on their side. :D :D
A nice gesture, but they wouldn't need you. ;)
Here is an AI version of Johnny Cash singing 'Barbie Girl'
https://www.youtube.com/watch?v=HW1qjsqS1zM (https://www.youtube.com/watch?v=HW1qjsqS1zM)
Here is an AI version of Johnny Cash singing 'Barbie Girl'
https://www.youtube.com/watch?v=HW1qjsqS1zM (https://www.youtube.com/watch?v=HW1qjsqS1zM)
I don't know whether to laugh or cry. The irony is good for a giggle (although I suspect the joke will wear thin pretty quickly), but come on ? Johnny Cash ? There really is nothing sacred left in this world.
This is where people get mashed up in the logic, they think Nano and AI are somehow on the same end of the spectrum, but they are polar opposites and always will be.
As intelligent as fruit fly might be, there is nothing to fear about nanobots and the like, tiny means low power, low energy, low strength. And Fruit Flies are Millibots or Microbots, thousands or hundreds of times bigger than Nano.
Nanobots are robots, robots on the nanoscale are not AI, never will be, they are not shrunk down tiny versions of CP30 or a submarine with lasers. No matter how smart the AI that might command a Nanobot or trillions or Nanobots, just one drop of soapy liquid ends the day horribly for them and stops them doing the singular thing they are engineered to do!
All the Nanobots that have ever been invented are ground to a halt by one single drop of detergent in a litre of water.
So if you harbour a fear of the unseen, have a shower, and if you are really paranoid try some Selsun Blue!
So there is no need to flocculant to those bad ideas!
(https://media.tenor.com/GRv73wcgKv0AAAAd/palmolive-youre-soaking-in-it.gif)
I asked the AI whether it was going to destroy humanity..
It was a bit each-way.
But, I'm not sure I trust it... ::)
The question of whether AI will destroy humanity is a complex one, and there are many different opinions on the matter. Some experts believe that AI could pose “profound risks to society and humanity” 1. Others have warned that AI could lead to the extinction of humanity 23. However, it’s important to note that these are just possibilities, and there is no guarantee that they will come to pass.
It’s also worth noting that many experts believe that AI has the potential to do a lot of good in the world. For example, AI could be used to help solve some of the world’s most pressing problems, such as climate change and poverty 1. Additionally, AI has the potential to make our lives easier and more convenient in many ways.
In conclusion, while there are certainly risks associated with AI, it’s important to remember that there are also many potential benefits. As with any new technology, it’s up to us as a society to ensure that we use it in a responsible and ethical manner.
This is where people get mashed up in the logic, they think Nano and AI are somehow on the same end of the spectrum, but they are polar opposites and always will be.
As intelligent as fruit fly might be, there is nothing to fear about nanobots and the like, tiny means low power, low energy, low strength. And Fruit Flies are Millibots or Microbots, thousands or hundreds of times bigger than Nano.
Nanobots are robots, robots on the nanoscale are not AI, never will be, they are not shrunk down tiny versions of CP30 or a submarine with lasers. No matter how smart the AI that might command a Nanobot or trillions or Nanobots, just one drop of soapy liquid ends the day horribly for them and stops them doing the singular thing they are engineered to do!
All the Nanobots that have ever been invented are ground to a halt by one single drop of detergent in a litre of water.
So if you harbour a fear of the unseen, have a shower, and if you are really paranoid try some Selsun Blue!
So there is no need to flocculant to those bad ideas!
3 strikes and you're out.
Stop thinking about the now.
I asked the AI whether it was going to destroy humanity..
It was a bit each-way.
But, I'm not sure I trust it... ::)
AI has the potential to do good, and could very much help with climate change.
You know what the easiest thing to combat climate change would be? Kill all humans! lol
Definition of 'good' and 'helping' are open to interpretation.....a simple misunderstanding could be all it takes.
You've seen enough episodes of Black Mirror to know how the best of intentions can go sideways very quickly and all so innocently enough.
3 strikes and you're out.
Stop thinking about the now.
Between Ukraine and Israel we'll be lucky to be here at Christmas
Between Ukraine and Israel we'll be lucky to be here at Christmas
In that podcast i referenced, and its from 2018 i believe, it talks about existential events and how different ones could occur and wipe out humanity for good.
Obviously, i've talked about AI.
They mentioned climate change.
The talk about the possibility of an asteroid ala Dinosaurs.
Aliens get a mention.
Pandemic gets a going over (again, pre-covid.....and they got so much of that right)
and all of this only matters if we don't wipe out ourselves via war first.
Also talks about the possibility that we are actually living in a simulation and we are not real. (Think Black Mirror, Hang the DJ)
Talks about 'the great filter' and 'the drake equation' before we even get into any of the above.
Its an honest, look at all things from a scientific and unbiased point of view without grandstanding and fear mongering....despite how it may appear.
You guys are talking about AI as it currently exists.
I'm talking about AI in the future, how far into the future is anybodys guess and its almost impossible to fathom.
Just like 100 years ago, it was impossible to fathom a contraption that could be used as a calculator doing basic mathematical operation any pre-schooler can do. When it eventually came to be, it was as big as a room. Now everyone carries that, and 100 other inventions capable of so much more, in their pocket.
What does 100 years from now look like??
30 years ago the thought of self driving cars was nothing more than sci fi nonsense. Now it exists.
Chat GPT is like the first fish that every crawled out of the water and onto land.
AI i'm talking about is humans taking over the planet.
There are a lot of steps from then to now, but it will happen. Time being the only unknown.
im talking about machines.
They don't think, they don't really learn, they just crunch numbers.
They can appear to be smart but they aren't.
The algorithms you've touched on that shape your thoughts so to speak are basic. They take an aggregate of what you've seen, and then show you more of what you've liked or seen before because the goal is to keep you watching and liking social media. They use data on your browser to feed you something you're interested in. The mics are on, and key words do get used to display something for you, but use a different browser without the trackers and it falls over.
Quantum computing may be a game changer but these things appear smart and intelligent,but they aren't actually intelligent. They can likely calculate a variety of diferent outcomes based on probability, data and information but they don't think, they don't learn and they can't really arrive at conclusion with intuition.
Will things change in future? Hard to say. The ability to act and react to situations absorbing everything happening around is still reliant on data of some type be it an input device, cameras or microphones and they are still going to utilise a predetermined set of instructions to do anything and if the instructions are written poorly it will end up in a loop or a situation where the machine crashes.
I will not trust my life in the hands of a driver less vehicle.
Technology has come a long way, but I can't trust the best device I've ever used to get things right and that's the smart phone in my pocket. It still does dumb crap.
im talking about machines.
They don't think, they don't really learn, they just crunch numbers.
They can appear to be smart but they aren't.
The algorithms you've touched on that shape your thoughts so to speak are basic. They take an aggregate of what you've seen, and then show you more of what you've liked or seen before because the goal is to keep you watching and liking social media. They use data on your browser to feed you something you're interested in. The mics are on, and key words do get used to display something for you, but use a different browser without the trackers and it falls over.
Quantum computing may be a game changer but these things appear smart and intelligent,but they aren't actually intelligent. They can likely calculate a variety of diferent outcomes based on probability, data and information but they don't think, they don't learn and they can't really arrive at conclusion with intuition.
Will things change in future? Hard to say. The ability to act and react to situations absorbing everything happening around is still reliant on data of some type be it an input device, cameras or microphones and they are still going to utilise a predetermined set of instructions to do anything and if the instructions are written poorly it will end up in a loop or a situation where the machine crashes.
I will not trust my life in the hands of a driver less vehicle.
Technology has come a long way, but I can't trust the best device I've ever used to get things right and that's the smart phone in my pocket. It still does dumb crap.
Ditto..especially to the driverless vehicle..
Quantum computing may be a game changer but these things appear smart and intelligent,but they aren't actually intelligent.
Agreed.
People think quantum computing is like general purpose computing, but it is not really going to be a game changer for General Purpose computing because the problem is the energy budget even if you solve the technical issues.
It takes a lot of juice to solve even a basic problem using quantum computing, so they will be targeted at very specific problems like crypto, molecular chemistry, medical or physics, etc., etc.. They will change these very niche areas, but they are unlikely to be used for day to day problems like current supercomputers or server farms.
Agreed.
People think quantum computing is like general purpose computing, but it is not really going to be a game changer for General Purpose computing because the problem is the energy budget even if you solve the technical issues.
It takes a lot of juice to solve even a basic problem using quantum computing, so they will be targeted at very specific problems like crypto, molecular chemistry, medical or physics, etc., etc.. They will change these very niche areas, but they are unlikely to be used for day to day problems like current supercomputers or server farms.
Quantum computing is where the AI really goes to the next level and now we are starting to think into the future.
That being said, i have to laugh at your bold comment. Reminds me of the initial comments about computers from IBM boss in the 40's.
"I think there is a world market for about five computers.
Once the cat is out of the bag....thats that.
Don't the 'Doomsday' predictions rely largely on a lack of vigilance on the part of humans at every stage of the AI progress and development.
If the buggers start their shenanigans we'll just take out their batteries ;) :D
Don't the 'Doomsday' predictions rely largely on a lack of vigilance on the part of humans at every stage of the AI progress and development.
If the buggers start their shenanigans we'll just take out their batteries ;) :D
Initially i did say without the lack of proper fail-safes. But it only takes one mistake, or one revenge driven former employee, or one Dr Evil to circumvent that.
I suspect that these will be running on a technology that we are not using yet, or at least is just theoretical.
Remember this stuff probably wont happen in our lifetimes. Batteries may be as 'old hat' then as horse driven carts are now. Around for novelty purposes only.
Don't the 'Doomsday' predictions rely largely on a lack of vigilance on the part of humans at every stage of the AI progress and development.
If the buggers start their shenanigans we'll just take out their batteries ;) :D
IF, THEN, AND, OR, ELSE statements.
That's all computers really do. IF variable condition with value open exists, THEN perform X AND/OR Y AND/OR Z, activities until variable condition changes to value close. Or something like that.
Do they learn? Well, you could argue that it will create a record of each outcome it performs an action for, and then review how to stop something from happening but it will be performed with another IF statement. Data corruption is more likely to end this whole thing than any other factor. Unplug the data and you unplug the ability for it to be intelligent.
What will quantum computing do? The above sort of parameters is capable of running in microseconds as it is, but the slow bit is the pipeline in, the collection of outcomes, and then after a certain number of outcomes have been collected, looking at them to see which ones are repeated, and what else could be done to stop the outcome from occurring. We are talking a few seconds to minutes of actions being collected, analysed and repeated all with scripting and coding.
The idea that they learn is not the same as someone learning something. We learn that fire is hot, and it is to be feared because when you get that feeling of going near something hot, it could hurt you. That instinct is not what the computer learns. It will learn a sequence of actions that get taken when something is hot to stop the thing from getting hot, or it will implement a sequence of actions to avoid the hot. It doesnt learn this, it finds that information and parrots it. You wipe the disk? The memory is gone? You have the smartest brick on the planet.
Where it gets murky is if someone starts leveraging AI without telling people and safe guards are built in to prevent things from happening, but ive seen far too many systems run into trouble because of stupid stuff.
i.e. A business builds a quantum computer server farm. This leverages all the hardware into a common purpose. That farm is unregulated but able to start doing whatever with only a few people's input. Form then on, how this pans out is largely dependant on whom is in control of that technology. Isolating it from the web is easy, but if it can resolve those issues and bypass security measures itself, then it opens itself up to all manner of input. Once it has the data how it will act is a bit of an unknown known. The programs and conditions it has committed to memory it will enact until conditions change, but the scripts it runs will largely be predetermined.
What Kruddler states about the technology is a mixed bag. I don't think we are going to see 2001: A space odyssey type stuff. The computers arent capable of rational, or irrational thought. They just perform instructions.
Case in point. At my place of employment, we run virtual servers in a microsoft data centre. They had an issue where one of the hosts had an issue and tried to fail us over. The operating system failed to start, and I had to restore the virtual machine from a backup and then perform remedial action to get its SQL server database back to normal. Luckily it was part of a pair, and the primary was happy as larry, and this was the secondary. It wasnt smart enough to realise that the cluster was repaired and to start reconciling the changes made on the primary to the secondary again without human interaction, and it was incapable of restoring itself from backup without interaction from us.
THAT is where these things are not that smart. According to Microsoft, the thing was fine and healthy but in reality the VM was in a failed to start mode that appeared fine.
Thry,
What you are talking about is basic computer programming. Done by humans, with fail safes involved and best of intentions.
New 'deep learning' or 'machine learning' doesn't work the same way.
These 'teach themselves' and we don't understand how they do it.
There are some basic examples of this, and some very advanced stuff.
For instance, there was one that was developed to 'model and predict' how some type of pendulum or rotationary machine worked.
As humans, we can describe it, model it and explain it.
The computer worked out its own way of modelling it and we don't know how it did it, but we know its different to our way.
It gets the right answer, we just have no idea how.
...and it worked it out by itself.
....and thats a very basic example.
I previously mentioned there is a type that can diagnose diseases from x-rays far better than humans. Not only that, it can do it on x-rays that have the resolution of something like PONG. As humans, we could barely work out what part of the body the x-ray is of, AI not only knows, but can predict what is cancerous with greater accuracy than the best trained doctors with the best technology.
Again, we don't know how.
These are very basic, just starting out levels of AI that are already showing up humans. How advanced will it be 20 years from now?40 years from now? 100 years from now?
20-25 years ago, i was trying to download an mp3 file and my 4hour dial-up reset would click in before that 6mb file would download....and i'd have to try again.
Now i can watch, in HD, a live video of same song/concert in real time, while other people in the same house are doing the same with their own interests being fulfilled equally well.
People are traditionally bad at predicting the future. Partially because the jobs of the future don't actually exist currently.
We project our own knowledge and expectations into the future, without reflecting on what occured over that same time period in the past.....and with the knowledge of technology increasing exponentially in the meantime.
Thry,
What you are talking about is basic computer programming. Done by humans, with fail safes involved and best of intentions.
New 'deep learning' or 'machine learning' doesn't work the same way.
These 'teach themselves' and we don't understand how they do it.
There are some basic examples of this, and some very advanced stuff.
For instance, there was one that was developed to 'model and predict' how some type of pendulum or rotationary machine worked.
As humans, we can describe it, model it and explain it.
The computer worked out its own way of modelling it and we don't know how it did it, but we know its different to our way.
It gets the right answer, we just have no idea how.
...and it worked it out by itself.
....and thats a very basic example.
I previously mentioned there is a type that can diagnose diseases from x-rays far better than humans. Not only that, it can do it on x-rays that have the resolution of something like PONG. As humans, we could barely work out what part of the body the x-ray is of, AI not only knows, but can predict what is cancerous with greater accuracy than the best trained doctors with the best technology.
Again, we don't know how.
These are very basic, just starting out levels of AI that are already showing up humans. How advanced will it be 20 years from now?40 years from now? 100 years from now?
20-25 years ago, i was trying to download an mp3 file and my 4hour dial-up reset would click in before that 6mb file would download....and i'd have to try again.
Now i can watch, in HD, a live video of same song/concert in real time, while other people in the same house are doing the same with their own interests being fulfilled equally well.
People are traditionally bad at predicting the future. Partially because the jobs of the future don't actually exist currently.
We project our own knowledge and expectations into the future, without reflecting on what occured over that same time period in the past.....and with the knowledge of technology increasing exponentially in the meantime.
kruddler I'm talking about how this works.
https://www.sas.com/en_au/insights/analytics/what-is-artificial-intelligence.html#:~:text=AI%20adapts%20through%20progressive%20learning,product%20to%20recommend%20next%20online.
Theres nothing that intelligent about it. It's all about the information you feed it.
kruddler I'm talking about how this works.
https://www.sas.com/en_au/insights/analytics/what-is-artificial-intelligence.html#:~:text=AI%20adapts%20through%20progressive%20learning,product%20to%20recommend%20next%20online.
Theres nothing that intelligent about it. It's all about the information you feed it.
Read the last part of that....
In summary, the goal of AI is to provide software that can reason on input and explain on output. AI will provide human-like interactions with software and offer decision support for specific tasks, but it’s not a replacement for humans – and won’t be anytime soon.
Based on CURRENT forms of AI.
Think longer term.
Here is a few quotes i found from people you may recognise...
“The pace of progress in artificial intelligence (I’m not referring to narrow AI) is incredibly fast. Unless you have direct exposure to groups like Deepmind, you have no idea how fast—it is growing at a pace close to exponential. The risk of something seriously dangerous happening is in the five-year time frame. 10 years at most.”
—Elon Musk wrote in a comment on Edge.org
“The development of full artificial intelligence could spell the end of the human race….It would take off on its own, and re-design itself at an ever increasing rate. Humans, who are limited by slow biological evolution, couldn’t compete, and would be superseded.”
— Stephen Hawking told the BBC
“I don’t want to really scare you, but it was alarming how many people I talked to who are highly placed people in AI who have retreats that are sort of ‘bug out’ houses, to which they could flee if it all hits the fan.”
—James Barrat, author of Our Final Invention: Artificial Intelligence and the End of the Human Era, told the Washington Post
“I’m increasingly inclined to think that there should be some regulatory oversight, maybe at the national and international level, just to make sure that we don’t do something very foolish. I mean with artificial intelligence we’re summoning the demon.”
—Elon Musk warned at MIT’s AeroAstro Centennial Symposium
There are a lot of people smarter than you or I than can see this as becoming an issue and i don't see any reason to doubt them.
Yes, neural networks and quantum computing rely on carefully crafted questions to deliver accurate responses.
Google conned the public a few years back claiming it's quantum engine solved a question in seconds that would take a conventional supercomputer decades. But the bogus nature of the claim was hidden in the detail. The Google quantum computer was designed and optimised to answer that specific question, in fact that is all it could do, and they used the unoptimised worst case scenario model for the Supercomputer.
If similarly optimised the Supercomputer would take about 2hrs, but the supercomputer can also answer General Purpose computing questions, while the quantum computer could not.
At the moment and into the foreseeable future quantum computers are task specific, like Hino selling one truck to carry bricks, and another truck that carries timber.
Read the last part of that....
Based on CURRENT forms of AI.
Think longer term.
Here is a few quotes i found from people you may recognise...
“The pace of progress in artificial intelligence (I’m not referring to narrow AI) is incredibly fast. Unless you have direct exposure to groups like Deepmind, you have no idea how fast—it is growing at a pace close to exponential. The risk of something seriously dangerous happening is in the five-year time frame. 10 years at most.”
—Elon Musk wrote in a comment on Edge.org
“The development of full artificial intelligence could spell the end of the human race….It would take off on its own, and re-design itself at an ever increasing rate. Humans, who are limited by slow biological evolution, couldn’t compete, and would be superseded.”
— Stephen Hawking told the BBC
“I don’t want to really scare you, but it was alarming how many people I talked to who are highly placed people in AI who have retreats that are sort of ‘bug out’ houses, to which they could flee if it all hits the fan.”
—James Barrat, author of Our Final Invention: Artificial Intelligence and the End of the Human Era, told the Washington Post
“I’m increasingly inclined to think that there should be some regulatory oversight, maybe at the national and international level, just to make sure that we don’t do something very foolish. I mean with artificial intelligence we’re summoning the demon.”
—Elon Musk warned at MIT’s AeroAstro Centennial Symposium
There are a lot of people smarter than you or I than can see this as becoming an issue and i don't see any reason to doubt them.
I'm still talking about how this works on a functional level.
The hello world component of it all. Function, algorithm, patterns, data, logic.
Apply that to people. They don't respond anywhere near as consistently because emotions, attachments, void of logical, empathy.
The hard disk is still just a library of instructions, which vary based on data, logic, and outcomes.
I've heard what you've stated. I see what those above have written and predicted. To a degree, uncontrolled I think it could get out of hand, but it would have to be so far removed from our current concept of a computer and how they work that it still isn't AI but a computer drawing bad conclusions, from faulty modelling. The exact opposite of intuitive knowledge and ergo not intelligent.
AI as it is currently being touted is dependant on LLM, massively parallel datasets that are trolled by massively parallel neural networks in the form of a Generative Adversarial Network, to construct algorithms and relationships between bits of data. But the LLM can't distinguish between reality and fantasy, and the dataset is not trivial. For example you could craft a question that would goad an AI into answering a question with facts relating to how bones of fire breathing dragons were found amongst dinosaur fossils.
Quantum computers are at the moment limited to a few hundred qubits, and they give instant answers to carefully crafted "questions", (This question is typically a conjecture expressed in math) but that questions can take weeks, months or years to get correct, and then take weeks, months or years to form a proof that both the question and the answer were correct. Think of the movie "The Man Who Knew Infinity."
At the moment Nano whatever works down to a molecular level, they are singular function devices that have zero intelligence or awareness.
That last word awareness is the critical term, because without awareness any system will be easily deceived no matter how well we craft it to be perceived as intelligent, and that is why our lauded AI LLM wonders can inform you "There be Dragons!"
If you want to worry about a technology going forward, probably nefarious enhanced humans might be your biggest threat, a uber brain in a complete bastard!
This AI debate reminded me of a lecture from Hannah Fry a few years back, I think part of the Royal Society Christmas Lecture series.
This video and others well worth watching;
https://www.youtube.com/watch?v=Rzhpf1Ai7Z4
Just had a listen to the new Beatles song "Now and Then"
Lennon's AI generated voice sounds tinny and artificial.
It only resembles the Beatles when the chorus kicks in but even then it's a pretty average song and more reminiscent of Lennon's post Beatles material.
It's still likely to be a hit, but sometimes it's better to leave well enough alone.
I had the weirdest experience with packet transfer this week at work. We have some SSL VPN tunnels which sends encrypted data from our on premises Firewall to our cloud provider. Effectively, the traffic to and from premises is encrypted and when data is transferred its broken up into ESP packets. These tunnels once established a fairly bullet proof and only re-authenticate without dropping. For about a week we started having an issue where we couldnt contact the cloud through that link, and ended up having to drop the tunnels and bring them back up to fix it. 20 minutes of down time each time, nothing too serious but then an investigation into root cause. The fact they re-established after dropping means configuration wasnt the issue.
Now these packets are encrypted, and the way it works is when you have large amounts of data, its broken up into smaller amounts, encrypted, and then sent down this tunnel via an internet connection, which will arrive the other side, and be re-assembled in order. The tunnel is a public connection with a public and private key pair. This is complex but not a big deal, nothing will usually go wrong there.
We ran some analysis, could see capture a log of traffic being sent by our firewall, and the cloud provider was not receiving them. After a couple of days of back and forth trying to work out where the break down was, and also contacting our internet service provider, we setup a sniffer in the middle that would intercept the packets and relay them down the line and upon checking those logs realised that everything fell over at the first hope. Firewall outbound seemed to not be happening even though it told us it was.
We have two of them in an active passive situation which will ensure if we lose one, stuff doesnt ever break. We failed over initially and it worked instantly (same config, same connections) and then failed back, and issue was present. So the (secondary)passive firewall was fine, and the active (primary) one started having the issue was resolved by simply turning it off, and turning it on again.
We are talking about a device, running a linux operating system, which has one job, that stopped doing its job and is usually the most robust component of the network, have a big issue. Now, you could argue that AI will re-write the code to prevent this from happening, but the problem is that everything looked fine, and actually wasn't.
THIS is why I don't think we will ever get to a point, where technology can do things properly without simply running commands, because even when we tell them to do something, they have a weird problem where they refuse to do the job they are employed for properly and a simply troubleshoot of drop and re-authenticate only worked for temporary restoration of services before we experienced another issue. Get these things with AI, and Im not sure how its supposed to analyse whats happening beyond its front door, when we had to implement more devices to actually tell us this information.
Just had a listen to the new Beatles song "Now and Then"
Lennon's AI generated voice sounds tinny and artificial.
It only resembles the Beatles when the chorus kicks in but even then it's a pretty average song and more reminiscent of Lennon's post Beatles material.
It's still likely to be a hit, but sometimes it's better to leave well enough alone.
I too had a listen. Always an admirer of The Beatles (who isn't) but not a huge fan (prefer the Stones). My opinion is that 'creating' a new song is better than having it left on an unlistenable cassette but it is hardly a great song.
I was interested to hear the other day 2 Brian Johnson ACDC songs with Bon Scott doing the vocals (via AI). Also a bit tinny sounding I thought but I always way preferred Bon vocals. Where will it end? Maybe me on lead vocals...
The problem ultimately becomes a debate about what is consciousness, at some very fine grained level we are all machines, dualism doesn't exist.
We break and we pass, despite millions of years of evolution to get every possible variant just right. Some human or AI designed code has no chance, because the chip it runs on is made from are the same sources of materials as all of us! Human or AI, we are all stardust.
In us a cosmic ray can cause cancer, for an AI a cosmic ray could be instantly fatal.
I've probably offended a large portion of the population just then, the technocrats and the religious! :o
Ironically, people are looking at this debate in binary fashion.
It works or it doesn't.
The possibility that AI could outperform humans quite easily, while still exhibiting some faults is a very real possibility that does not alleviate the exestensial concerns.
Nobody said AI would be infallible.
Of course....
It's not infallible...its a developing thing...and the ability to reproduce artists work will get better.
McCartney was asked whether he thought John would be on board with the project and his response was an emphatic 'yes.'
It then becomes a matter of an intellectual legacy.
Once an artist passes do they 'or surviving family' have any control how their voices are used and what songs they 'perform'.
They might find the material totally against their style even beliefs...but does it matter, because they're dead?
Ironically, people are looking at this debate in binary fashion.
It works or it doesn't.
The possibility that AI could outperform humans quite easily, while still exhibiting some faults is a very real possibility that does not alleviate the exestensial concerns.
Nobody said AI would be infallible.
for my experience above you'll never see me in a driverless vehicle.
for my experience above you'll never see me in a driverless vehicle.
That becomes a debate about repetition and reliability, because it's about robotics not AI.
There's a simple philosophy thought experiment related to Occams Razor, built on the concept of the atom.
How many time can you be divided and consciousness remains, when are the pieces so small consciousness goes away?
Not sure if anyone is aware, but this was done over 10 years ago.
https://www.youtube.com/watch?v=P18EdAKuC1U
That becomes a debate about repetition and reliability, because it's about robotics not AI.
There's a simple philosophy thought experiment related to Occams Razor, built on the concept of the atom.
How many time can you be divided and consciousness remains, when are the pieces so small consciousness goes away?
Mate, the firewall wigging out and dropping esp packets, is how the driverless vehicle is going to receive external information securely to prevent it being "hacked".
Those tunnels have been bullet proof for 12 months. The IT world is an ever evolving beast but that made no sense.
Check out what an IP sec tunnel is. It's dry reading but illuminating.
https://www.cloudflare.com/en-au/learning/network-layer/what-is-ipsec/
Check out the final Beatles video clip, done by Peter Jackson with a lot of AI.... so good....
https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B (https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B)
Watch it through to the end.....
Check out the final Beatles video clip, done by Peter Jackson with a lot of AI.... so good....
https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B (https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B)
Watch it through to the end.....
It's a nice song. Certainly even the "worst" of the Beatles never dips below a certain level of greatness, but I find the production a little jarring. Maybe it's just the shock of the new. Lennon's vocals from 1974, Harrison's guitar parts from 1994, Paul and Ringo from 2023. And they all sound of their time. The bass, piano and drums sound modern, like anything recorded now. I'm glad they did it, but it neither adds nor detracts to my fondness for the Beatles.
I too had a listen. Always an admirer of The Beatles (who isn't) but not a huge fan (prefer the Stones). My opinion is that 'creating' a new song is better than having it left on an unlistenable cassette but it is hardly a great song.
I was interested to hear the other day 2 Brian Johnson ACDC songs with Bon Scott doing the vocals (via AI). Also a bit tinny sounding I thought but I always way preferred Bon vocals. Where will it end? Maybe me on lead vocals...
In a way, I also prefer listening to the Stones, but the two bands are on different planes IMO. The Stones were a great band, but the Beatles changed popular music forever. I think part of the reason the Stones are more user friendly is that they never really stray too far from their roots. They were, as Elvis Costello so wonderfully put it, "rabid RnB evangelists." The Beatles were genre busting, boundary pushing musical geniuses IMO.
That's probably true...
You can hear a Stones song and can tell almost straight away it's the Stones.
It's a sound that's endured over decades.
The Beatles went through such a range of different sounds in the short time (less than ten years) that where together that where they finished up was 'chalk and cheese' to where they started.
That's probably true...
You can hear a Stones song and can tell almost straight away it's the Stones.
It's a sound that's endured over decades.
The Beatles went through such a range of different sounds in the short time (less than ten years) that where together that where they finished up was 'chalk and cheese' to where they started.
The period of time when the Beatles decided to move away from mop top teen sensations, to serious musicians determined to push themselves to the limit, is the most spectacular transformation in pop music history. They were influenced by Bob Dylan's super trilogy of mid 60's recordings. U2 and Radiohead have followed suit and also went through a transformation in their careers.
Check out the final Beatles video clip, done by Peter Jackson with a lot of AI.... so good....
https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B (https://www.msn.com/es-mx/noticias/mexico/the-beatles-now-and-then-official-music-video/vi-AA1jlY2B)
Watch it through to the end.....
The song is pretty good, but the film clip is fantastic. Peter Jackson , take a bow....
Yep, great clip. The song's sentimentality reminded me immediately of George Harrison's When we were fab from the late 80s.
It's kind of wierd listening to it because it feels like a post Beatles song, but just by one of them until there are some quite typical Beatles structure/progressions to it.
In the 90s, there was also Natalie King Cole singing Unforgettable 'with' her father, which was considered ground breaking.
This is taking things to a new level - pretty fascinating how they are able to do all that.
In the 90s, there was also Natalie King Cole singing Unforgettable 'with' her father, which was considered ground breaking.
Gina & Vizard did it better… 🤣
https://twitter.com/i/status/1728089499429642432
Obviously, AI doesn't stop you being shizen!
But I'm not actually sure what is more shizen, the AI or the person trying to script the result! ;D
It's a bit of a dirge...but it's not the worst song. I'd actually like to hear it on vinyl. :D
.......................... I'd actually like to hear it on vinyl. :D
At least then you could throw it at the wall when you're done! ;D
Obviously, AI doesn't stop you being shizen!
But I'm not actually sure what is more shizen, the AI or the person trying to script the result! ;D
It just needs to release a sex tape and then it can replace the modern day pop stars completely.
The music is equally bad and 'paint by numbers' as the rest of the crap that is released nowadays so go the whole 9 yards with it and replace them altogether.
Who needs a body double anymore ::) ;D
https://www.msn.com/en-us/news/world/putin-confronts-his-ai-double/ar-AA1lvjJw
As many of you know I'm not a big fan of the media, in fact I've grown to loath it. But I have to say they taken low to a new lower level recently with the storm in a teacup Royal Photo agenda.
Now before we get into the technical, is it just me or could it be the media is just a tad hypocritical about altering photographs? :o
Any techno savvy person already knows what is happening here, in fact we've seen it advertised on TV. You know the Google or Apple phone that takes a bunch of bracketed shots and gives you a selected mix of singularly blissful perfection. Swap your frown turn it upside down AI to the rescue, cut grumpy distracted kid reinsert blessed angel, just swipe. All on auto if you are willing to surrender to your new digital overlords! ;)
Me thinks there might be a few In-House royal photographers who a feeling a little miffed at the royal selfie trend, and are willing to beat-up spill the beans. You can hear the grinding of royal photographer teeth even here in the antipodes! :D
The amount of these random rants you go on that i have absolutely no idea what you are on about it remarkable.
In this instance, i couldn't care less about it because its about the royals. But if i did, i wouldn't know what you are on about.
You don't like the media? No!
I don't like the media....so i don't read it, watch it, whatever.
So maybe everyone else knows what you are on about and i'm the only one who doesn't....or maybe everyone else is on the same page as you.
Either way, maybe post a link or SOMETHING in the future.