-
Dear Guest, Please note that adult content is not permitted on this forum. We have had our Google ads disabled at times due to some posts that were found from some time ago. Please do not post adult content and if you see any already on the forum, please report the post so that we can deal with it. Adult content is allowed in the glory hole - you will have to request permission to access it. Thanks, scara
Artificial intelligence
- Thread starter Daisuk
- Start date
Just one?
We are Tottenham
Eidur Gudjohnsen
Is there such a thing as AI???
It can't be Intelligent can it?
because it is artificial!
It can't be Intelligent can it?
because it is artificial!
Would you like to expand on that?
We are Tottenham
Eidur Gudjohnsen
Just noted it was obvious to me the fact it is called artificial.
I had this conversation with a boss I used to work after watching a programme on TV about AI way back in the late sixties.
As at that time there was a lot of speculation about that time with the knowledge that computers would have a massive impact on society. Not less so the Workplace. Anyway, they were saying that in time they could make computers or indeed machines that could think. I had to question my wise mentor his thoughts and was surprised for him to say he thought it was possible because after all the brain worked by taking in information in a similar manner
0s and ones.Anyway I thought he was trying me out at the time because to me I just could not see how a machine could think like a Human.
I still can,t see how that is possible somehow even now though I have little knowledge of computers.
It revolves around how life started really and I am not so sure Scientist have. Found the answer,this is without getting in to any religious discussion on the subject.
I know you help set up glory glory so you must have some thoughts.. Views on this and I bet you think AI is possible
I am not so sure..where's the proof?
CoySpurs..lol.
@We are Tottenham A lot to unpack in your paragraph
- First up its very hard to truly compare machines to humans, mostly because we don't fully understand how our brain works at this point.
- Machine's can't think, but they can solve problems and the big applicable piece in AI is machine learning. Simple example, in the past you had some data you input, and you gave the machine very specific rules on how to transform that data into some kind of result, then simply based on the speed of transaction, the machine did the work. Today we can give the machine data input and samples of what we want the result to look like and it will figure out how to transform it, the bigger the sample and data sizes, the better it gets.
- A lot of people mistake AI with a machine becoming self aware, right now there is no logical path I see between AI/ML and a machine suddenly becoming self aware.
The main point is AI makes a machine do things that seem human or at minimum was previously very difficult for machines to do, it doesn't make them alive/real/self aware/however you would describe it.
- First up its very hard to truly compare machines to humans, mostly because we don't fully understand how our brain works at this point.
- Machine's can't think, but they can solve problems and the big applicable piece in AI is machine learning. Simple example, in the past you had some data you input, and you gave the machine very specific rules on how to transform that data into some kind of result, then simply based on the speed of transaction, the machine did the work. Today we can give the machine data input and samples of what we want the result to look like and it will figure out how to transform it, the bigger the sample and data sizes, the better it gets.
- A lot of people mistake AI with a machine becoming self aware, right now there is no logical path I see between AI/ML and a machine suddenly becoming self aware.
The main point is AI makes a machine do things that seem human or at minimum was previously very difficult for machines to do, it doesn't make them alive/real/self aware/however you would describe it.
Kandi1977
Garth Crooks
Artificial sweetener isn't sugar, but it's still a sweetener. It's the same with artificial intelligence. It's just a different kind of intelligence.
In order for that to be true, you would have to show that there is something different or special about human intelligence.
To my knowledge, nobody in the field seems to think that.
NoLimits01
Goran Bunjevcevic
As it already been said the bot opening the door is just responding to a pre-programmed problem, the intelligence bit is how the programming is done (I believe they used a simple(!) neural matrix) that allows the bot to identify it surroundings, assess angles and position and complete predefined movements to reach its goal.
For me the really exiting bit of the video isn't it opening the door but how fluid it's walking and balancing was, especially when pulled and pushed, don't underestimate how difficult that is to do (speed of cross processing between the gyros is very impressive)
The really exiting AI stuff will come with the next generation of Quantum Computing and Neural Networking where the network (or matrix) is not fixed in advance but adapts through a process of trial and error, but this could be some way off, today Quantum Machine Learning is currently used by research and scientific organisations such as CERN and is being developed by Google and Microsoft for Massive Analytical Engines to predict human behaviour.
There are loads of good articles out there by people like Seth Lloyd of MIT and Hartmut Neven of Google also worth checking out Quanta Magazine for the odd AI/QI and ML article
For me the really exiting bit of the video isn't it opening the door but how fluid it's walking and balancing was, especially when pulled and pushed, don't underestimate how difficult that is to do (speed of cross processing between the gyros is very impressive)
The really exiting AI stuff will come with the next generation of Quantum Computing and Neural Networking where the network (or matrix) is not fixed in advance but adapts through a process of trial and error, but this could be some way off, today Quantum Machine Learning is currently used by research and scientific organisations such as CERN and is being developed by Google and Microsoft for Massive Analytical Engines to predict human behaviour.
There are loads of good articles out there by people like Seth Lloyd of MIT and Hartmut Neven of Google also worth checking out Quanta Magazine for the odd AI/QI and ML article
BrainOfLevy
Michael Carrick
So who here works in tech? Either software, infrastructure of some other kind of VC / PE backed industry disruptor?
I feel like I may as well get some useful industry connections for all the time I spend on here arguing about whether Sissoko is any good or not...
I feel like I may as well get some useful industry connections for all the time I spend on here arguing about whether Sissoko is any good or not...
Lemonade Money
Dimitar Berbatov
You might call Sissoko an MP backed industrial disrupter.
I do .. lets say a significant software company with major investments in this area (amongst others) ...
Robbo
Paul Walsh
Just read this long and very interesting story on AI in the New York Times:
A.I. Is Mastering Language. Should We Trust What It Says? https://nyti.ms/37SdY3M
Not expecting Skynet anytime (too) soon, but this article raises a lot of questions about the development of AI. I've also ventured into the OpenAI website for the first time, and found some of the examples very fascinating. I do however question the intelligence of AI after seing its answer to this question about Spurs.
Me: If you take the history of Tottenham Hotspur into consideration, including past successes and failures, how would you describe the inherent mentality of the club and its players?
AI: The mentality of Tottenham Hotspur and its players can be described as resilient. The club has a history of overcoming adversity and bouncing back from setbacks. Its players have a never-say-die attitude and are always looking to fight for the win.
A.I. Is Mastering Language. Should We Trust What It Says? https://nyti.ms/37SdY3M
Not expecting Skynet anytime (too) soon, but this article raises a lot of questions about the development of AI. I've also ventured into the OpenAI website for the first time, and found some of the examples very fascinating. I do however question the intelligence of AI after seing its answer to this question about Spurs.
Me: If you take the history of Tottenham Hotspur into consideration, including past successes and failures, how would you describe the inherent mentality of the club and its players?
AI: The mentality of Tottenham Hotspur and its players can be described as resilient. The club has a history of overcoming adversity and bouncing back from setbacks. Its players have a never-say-die attitude and are always looking to fight for the win.
SpurMeUp
Gary Stevens
Just read this long and very interesting story on AI in the New York Times:
A.I. Is Mastering Language. Should We Trust What It Says? https://nyti.ms/37SdY3M
Not expecting Skynet anytime (too) soon, but this article raises a lot of questions about the development of AI. I've also ventured into the OpenAI website for the first time, and found some of the examples very fascinating. I do however question the intelligence of AI after seing its answer to this question about Spurs.
Me: If you take the history of Tottenham Hotspur into consideration, including past successes and failures, how would you describe the inherent mentality of the club and its players?
AI: The mentality of Tottenham Hotspur and its players can be described as resilient. The club has a history of overcoming adversity and bouncing back from setbacks. Its players have a never-say-die attitude and are always looking to fight for the win.
New AI is amazing, yet its also increasingly apparent that it has limitations.
AI made chess engines truly superb. Computers were already better than humans at chess. But self-learning AI took chess engines onto another level, playing in creative exciting ways. And the machine taught itself to do this. My post is being corrected by 'AI' software that learns about how humans misspell words. These kinds of closed 'systems' are where AI works. With clearly defined boundaries and experience, AI works better than human brains. But...for conversation that is more than a party piece, or to really drive a car safely, AI is nowhere near being autonomous. The many many variables and complexities make it hard to learn or program. Because 90% of driving a car can be done by a machine, car companies proudly proclaimed they will launch a fully autonomous car in the next 6 months, next year, next 2 years. Each year it is supposedly just around the corner. Despite the billions of investment and many many companies racing to achieve it, it is miles off. We probably won't see fully autonomous driving - as we dive today - in our lifetimes imo. AI works best in confined areas where we can define the parameters easily. So starting and stopping in traffic, following other cars and adapting speed on a motorway etc will semi-automate driving, but all the complexity of when to stop for someone crossing and when not to, driving around obstacles or road works etc. will still rely on our grey matter for the foreseeable.
Robbo
Paul Walsh
I agree on that last part - there is a lot of hype surrounding AI, and probably will be for the forseable future.
What I find interesting from the article, is that they've created an AI that is able to string together coherent and mostly meaningful sentences without being fed data on how to write. It has basically taught itself correct grammar, punctuation and correct sentence structure, with a vocabulary to go with it. And it's apparently not just copy and paste from the internet either, if you are to believe the story.
I tried one of their chatbots too, and found myself in what felt like a reasonably normal conversation with something that identified itself as a 14 year old girl. (no poor jokes, please, it/she told me about her dream to become a history teacher) It felt at times as if I was chatting to a human, while other times the replies were nonsensical and clearly coming from a computer.
Whether either of this counts as "intelligence" is highly debatable, but the field of AI is definitely progressing. I think we'll see some major breakthroughs in the next 10-20 years though. That's my (uninformed) view anyways. brick is moving fast these days.
A lot of the advances relied on moores law continuing. That has slowed. Computers are not advancing at the speed they had been for 50 years, meaning ai wouldn't advance as fast as expected.
Quantum computing or at least a mish mash, might speed up the advcement of computing again. We'll see. If not it's doubtful we see artificial general intelligence any time soon let alone artificial super inteligence.
Quantum computing or at least a mish mash, might speed up the advcement of computing again. We'll see. If not it's doubtful we see artificial general intelligence any time soon let alone artificial super inteligence.