Jump to content

The great AI content theft debate


Andrew Reid
 Share

Recommended Posts

EOSHD Pro Color 5 for Sony cameras EOSHD Z LOG for Nikon CamerasEOSHD C-LOG and Film Profiles for All Canon DSLRs

Feeding the devil so it can unfold, means, it´s still the devil. A bully thief and murderer. No admiration for that. Elton Murks is the ultimate murks man, hyper privilged narcist. Him and the other narcists already buying islands, bunkers and shit to survive the ai shit they started. ai is stupid. no matter what it will be able to process and spit out. The term white privileged cis man really makes sense in this regard. No one seems to care. Shame.

Link to comment
Share on other sites

I love this point of yours, Andrew. AI killing the most enjoyable jobs now, making joyful acitivities to earn money impossible. To be able to proceed, means making the AI more and more powerful, self empowerment is empowering the AI even more that way, as AI will be fed with data from more and more human acitivity.

Alternative is to forbid it in certain fields, like a ban on nuclear weapons.

Link to comment
Share on other sites

N

6 minutes ago, newfoundmass said:

Indeed, there are quite a few troubling signs when it comes to AI and the way it will be used in the future. To me, there is a lot of promise in AI as long as it's used as merely a TOOL or aid to the person. It's disappointing, but not at all surprising, that it is being viewed as a replacement for the person completely.

Never abandon cash for that reason. If they try to forbid cash money, we have to vote for a different goverment. Apple pay, yikes. Only if you give the all of us beautiful escape luxury island and later a starship to a better unpoluted planet. Not happening. Free speech becomes very dangerous, to be exposed to these data hungry AIs btw.

Link to comment
Share on other sites

  • Administrators
18 minutes ago, newfoundmass said:

Indeed, there are quite a few troubling signs when it comes to AI and the way it will be used in the future. To me, there is a lot of promise in AI as long as it's used as merely a TOOL or aid to the person. It's disappointing, but not at all surprising, that it is being viewed as a replacement for the person completely.

Tech starts off as a toolset and morphs into an all consuming culture. Much of the way we live our lives today is shaped by technology. A simple tool for convenience is how it gets a foothold and then before you know it... plenty of unintended consequences.

When the internet was merely a tool for example, before social media, it didn't have as large impact on culture, politics and people's social lives. It was ticking along as a knowledge-base, a store front and a source of entertainment quite nicely.

Then suddenly you have people working from home, socialising from home, and when they do venture outside, they are staring at their phone constantly.

Here's how I think AI will develop.

Step one, is the complete obliteration of Google, they are the next Blackberry. That's not to say they won't have skin in the game, but you can be sure (as ChatGPT is showing) that as the "establishment" they will always be a step behind the cutting edge like Nokia vs Apple. Google can't even get their established products working well. Search is a total mess. YouTube isn't fulfilling full potential, and their smartphone business is a bit player even after all this time.

Step two, is widespread unemployment. Companies simply won't need as many staff any more. Some jobs will be entirely obsolete. Going to be fun!

Step three is where it takes a physical form. Starting with the very rich, they will be able to train a physical form of AI to go out and simply do their job for them whist they sit at home drinking gin.

Step four is the complete replacement of all human beings.

Link to comment
Share on other sites

  • Super Members

In the short to medium term there will be plenty of opportunities for people to have careers as editors of the Ai output.

None of the code that I've experimented with it generating has actually worked (or even compiled) without me finessing it and anything creative I've prompted it to do has shown a propensity to frequently - and wildly - overestimate the number of limbs/fingers humans have and the extent of their range of articulation.

It has also had a bizarre and somewhat disturbing penchant for creating faces in scenes of crowds where one of them has more than a passing resemblance to the former leader of the National Socialist party.

Link to comment
Share on other sites

8 hours ago, BTM_Pix said:

 

In the short to medium term there will be plenty of opportunities for people to have careers as editors of the Ai output.

None of the code that I've experimented with it generating has actually worked (or even compiled) without me finessing it and anything creative I've prompted it to do has shown a propensity to frequently - and wildly - overestimate the number of limbs/fingers humans have and the extent of their range of articulation.

It has also had a bizarre and somewhat disturbing penchant for creating faces in scenes of crowds where one of them has more than a passing resemblance to the former leader of the National Socialist party.

 

This quote highlights the current limitations of AI technology and its potential for creating biased or unexpected outputs. While there may be opportunities for individuals to work as editors of AI output, the author's experience suggests that there is still a long way to go before AI can produce high-quality and reliable results without human intervention. Additionally, the mention of a disturbing output highlights the importance of ethical considerations and the need to address potential biases in AI systems. Overall, the quote suggests that while AI has the potential to revolutionize many industries, it is important to approach its development and deployment with caution and to carefully consider the potential consequences of its outputs.

Link to comment
Share on other sites

Explaining dynamic range to a 4-year-old is apparently possible thanks to ChatGPT:

Hey kids! Do you know what a camera is? It's a tool that helps us take pictures and capture memories. But do you know what "dynamic range" means in a camera? Well, let me explain it to you in a fun way!

Imagine you're playing outside on a sunny day. You see a big, beautiful tree that you want to take a picture of. But when you look through the camera, you see that the tree is too bright and you can't see the details of the leaves and branches. That's because the sun is too strong and it's hard for the camera to capture all the details in the bright light and the dark shadows.

This is where dynamic range comes in! Dynamic range is the amount of light that a camera can capture. A camera with a high dynamic range can capture both the bright parts and the dark parts of a scene, so you can see all the details.

Think of it like a cookie jar with a big opening. The bigger the opening, the more cookies you can fit in the jar! Similarly, a camera with a high dynamic range can fit in more light and capture more details in a picture.

So the next time you take a picture, remember to look for a camera with a high dynamic range so you can take pictures that show all the details, even in bright sunlight!

Link to comment
Share on other sites

Now the prompt is ridiculous: "Explain dynamic range to a 4-year-old, adding in facts about American History."

 

Hi kids! Do you know what a camera is? It's a tool that helps us take pictures and capture memories. But have you heard of "dynamic range"? Well, let me tell you all about it while we learn about American history!

Back in the days of the American Civil War, photographers had a hard time taking clear pictures because the cameras of that time couldn't capture all the details in the bright sunlight and dark shadows. But, over time, cameras got better and better, and dynamic range became a big part of that.

Dynamic range is the amount of light that a camera can capture. Just like how the American colonists fought for their independence and the right to control their own lives, a camera with a high dynamic range can capture both the bright parts and the dark parts of a scene, so it has control over all the details in the picture.

Think of it like the American Dream - the bigger the opportunity, the more you can achieve. Similarly, a camera with a high dynamic range can fit in more light and capture more details in a picture, just like how Americans have the opportunity to chase their dreams and achieve their goals.

So the next time you take a picture, remember the spirit of American history and look for a camera with a high dynamic range, so you can capture all the details and make your own memories, just like our forefathers did!

Link to comment
Share on other sites

15 hours ago, Andrew Reid said:

Here's how I think AI will develop.

Step one, is the complete obliteration of Google, they are the next Blackberry. That's not to say they won't have skin in the game, but you can be sure (as ChatGPT is showing) that as the "establishment" they will always be a step behind the cutting edge like Nokia vs Apple. Google can't even get their established products working well. Search is a total mess. YouTube isn't fulfilling full potential, and their smartphone business is a bit player even after all this time.

Let's not forget that ChatGPT is built entirely on Google developed science. Google still have many of the top machine learning R&D people. It is premature to write them off. I'm absolutely certain that Google can deploy and optimize LLMs for scale in a way few other companies can. All they need is incentive, and now they also have that.

 

re: Bard model errors

It is certainly a failure to have this happen in a presentation, but ChatGPT makes stupid mistakes all the time. Here is a good writeup with some blatant examples by Wolfram: https://writings.stephenwolfram.com/2023/01/wolframalpha-as-the-way-to-bring-computational-knowledge-superpowers-to-chatgpt/

 

Link to comment
Share on other sites

  • Administrators

This is a good article and really spells out what's at stake

https://www.businessinsider.com/ai-chatbots-chatgpt-google-bard-microsoft-bing-break-internet-search-2023-2

How on earth will independent blogs, magazines, review sites, forums and pretty much everyone else get noticed in an era of ChatGPT taking over from traditional web search?

It's the beginning of the end for user generated content outside of social media platforms.

Very sad indeed.

Link to comment
Share on other sites

  • 2 weeks later...

"When you’re fundraising, it’s AI. When you’re hiring, it’s ML. When you’re implementing, it’s linear regression."

Replace "fundraising" with "marketing" and the truth value doesn't change. It is "artificial intelligence" as much as your phone or watch is "smart". Which is none.

So the answer is "No, it isn't", but it largely depends on definitions and heavily overloaded semantics. "AI" certainly doesn't "think", nor "feel", but it can "sense" or "perceive" by being fed data from sensors, and it can represent knowledge and learn. The latter two are where the usefulness comes from, currently. A model can distill structure from a dataset in order to represent knowledge needed for solving a specific task. It is glorified statistics, is all. But anthropomorphizing is in our DNA, we have a sci-fi legacy imprinted on us, and model design itself has long been taking cues from neurobiology, so you'll never be able to steer terminology in the field towards something more restrained.

Link to comment
Share on other sites

On 2/18/2023 at 12:24 PM, cpc said:

"When you’re fundraising, it’s AI. When you’re hiring, it’s ML. When you’re implementing, it’s linear regression."

Replace "fundraising" with "marketing" and the truth value doesn't change. It is "artificial intelligence" as much as your phone or watch is "smart". Which is none.

So the answer is "No, it isn't", but it largely depends on definitions and heavily overloaded semantics. "AI" certainly doesn't "think", nor "feel", but it can "sense" or "perceive" by being fed data from sensors, and it can represent knowledge and learn. The latter two are where the usefulness comes from, currently. A model can distill structure from a dataset in order to represent knowledge needed for solving a specific task. It is glorified statistics, is all. But anthropomorphizing is in our DNA, we have a sci-fi legacy imprinted on us, and model design itself has long been taking cues from neurobiology, so you'll never be able to steer terminology in the field towards something more restrained.

I am struggling to see any value in my life - if I am researching something I want to look at various sources (and really importantly, vet them) and come to my own conclusion based on the evidence, and present that evidence accordingly if need be, combined with my own reasoning. These chat bots regurgitate stuff (from wherever but presumably via someone's idea of what is reliable, but not mine), very cleverly, addressing what is asked, and that's it, as if it is 'the answer' (though may be based on rubbish but we have no idea as there is zero transparency - the potential for manipulation is huge) - the worst kind of research tool.

I suppose it is OK for casual enquiry and for those who want to write bland bollocks that isn't worth writing in the first place. but we somehow seem to think is required.  It would be great for political speeches and responses that sound good but say nothing and for those 'statements' put out by government and other institutions in place of actually having to face an interview.

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

 Share

  • EOSHD Pro Color 5 for All Sony cameras
    EOSHD C-LOG and Film Profiles for All Canon DSLRs
    EOSHD Dynamic Range Enhancer for H.264/H.265
×
×
  • Create New...