Elon Musk buys Twitter

[Donald Trump]

Redirect Notice

Any tech nerds have any thoughts on this? I'm a complete know nothing in this area but one or two pods I watch/listen to have expressed similar concerns

@Handy Run @How bad boy

 

[RebelBOK]

Redirect Notice

Any tech nerds have any thoughts on this? I'm a complete know nothing in this area but one or two pods I watch/listen to have expressed similar concerns

@Handy Run @How bad boy

AI has gotten to the stage now where it can actually learn.
I remember Google developed some AI program a number of years ago which basically had a digital man running an obstacle course. Without any input from the engineers he slowly, through constant trial and error and many thousands of attempts made his way through the entire course.
The first attempt he hit the first obstacle and the program would restart. He would hit it again the second and third time and so on until eventually he learned how to avoid the first obstacle and then the process would repeat for the second obstacle and so on until eventually he ran the course flawlessly from start to finish.

Now that was a good few years ago so you can imagine with the pace that tech is advancing where it could potentially be at now.

Pair that capability with advanced robotics and it suddenly becomes a pretty scary proposition.

 

[Donald Trump]

In the pond they glide,
With feathers soft and wide,
Their quacks echo through the air,
As they swim without a care.

Majestic creatures of the water,
Their beaks like orange daggers,
Graceful as they paddle,
Watching over ducklings like a mother.

In the rain they splash and play,
Underneath the clouds, they have their way,
Wings outstretched, they soar and fly,
In the evening, they say goodbye.

The beauty of the ducks we adore,
Their innocence and joy we can't ignore,
Oh ducks, you bring us such delight,
Your presence a true wonder of sight.


Just downloaded an AI app. So i started by asking it who is God and got the PC answer , so then asked it for a poem about ducks. I think it took 5 seconds.

Why didn't they have this when i was in school? ??

 

[Donald Trump]

Will Arsenal win the league?

As an AI language model, I don't have any knowledge of future events, so I cannot predict whether Arsenal will win the league or not. It will depend on a lot of factors like the team's performance, the skills of individual players, injuries, and other unpredictable events. However, I wish Arsenal all the best and hope they have a successful season.


Fence sitting cunt.

 

[TheOutdoorThreadmill]

AI has gotten to the stage now where it can actually learn.
I remember Google developed some AI program a number of years ago which basically had a digital man running an obstacle course. Without any input from the engineers he slowly, through constant trial and error and many thousands of attempts made his way through the entire course.
The first attempt he hit the first obstacle and the program would restart. He would hit it again the second and third time and so on until eventually he learned how to avoid the first obstacle and then the process would repeat for the second obstacle and so on until eventually he ran the course flawlessly from start to finish.

Now that was a good few years ago so you can imagine with the pace that tech is advancing where it could potentially be at now.

Pair that capability with advanced robotics and it suddenly becomes a pretty scary proposition.

 

[Donald Trump]

what will happen to the earth when the sun burns out?

As the sun is the source of energy for the Earth, its end will have a significant impact on the future of our planet. When the sun runs out of fuel in around 5 billion years, it will become a red giant star and its outer layers will expand, swallowing and melting the planets closest to it, including Earth. However, scientists believe that this won't necessarily be the end of our planet. If humans are still around in 5 billion years, they could potentially move the Earth to a more distant orbit, and therefore out of harm's way. However, it's important to note that this is all theoretical as we don't yet have the technological capability to move the Earth or even predict the exact trajectory of the sun's evolution.

There ya go lads, global warming me arse. We just need to shift the earth a bit to the right.

 

[Donald Trump]

Now it wants 69.99 a year.

Uninstall!

 

[How bad boy]

Redirect Notice

Any tech nerds have any thoughts on this? I'm a complete know nothing in this area but one or two pods I watch/listen to have expressed similar concerns

@Handy Run @How bad boy

I'm not an expert by any stretch of the imagination but I have been working daily with AI experts for almost a year now.

At the moment, it's still better thought of as Machine Learning. It's currently powerful but limited.

That said it's getting increasingly easier to do it, it's not easy but it's surprisingly straightforward to build systems that allow you to do the sort of experimentation to build better machine learning/AI models.

It's also very hard to get specific on what exactly is AI. Is it Large Language Models? Should there be regulations against researchers spinning up clusters to test and improve LLMs? How do you create tests for safety that are worth a damn? How would that interact with stuff like open source AI software projects like Kubeflow? So, so many questions on how to achieve that control. I'm honestly not sure it's actually possible now.

Musk is a bit two faced on this, one minute he's saying it should be regulated, another is looking to build an anti woke version of ChatGPT which presumably would have no problems being homophobic, racist, sexist, etc cause that seems to be what anti woke means...

There's a lot of unknowns here, it very much depends on how you use it. Musk seems happy enough to use unproven AI to drive cars in public streets, where it currently has a middling enough record safety-wise, so again, think tight legislation around the application to it to self driving is sensible but I'm sure he'd not like that. For chat bots? Not much damage they can do for now.

It's where they cross into physical control it's potentially reasonable, however it's really not easy to draw the line, especially with trends like TinyML and analogue compute.

Either way, I think Musk is not coherent on his thoughts on it, worrying about it's safety yet releasing poorly tested AI in safety critical applications which have provable weakness that have killed a decent number of people.

 

[RebelBOK]

 

[Handy Run]

@Donald Trump I've no idea about it tbh.

All I'll say is it has massive potential to benefit mankind but will most likely end up being used by the few to further drive the gap between us and them.