Posted on 06/23/2023 3:36:18 AM PDT by RoosterRedux
Artificial intelligence has a racial bias problem.
From biometric identification systems that disproportionately misidentify the faces of Black people and minorities, to applications of voice recognition software that fail to distinguish voices with distinct regional accents, AI has a lot to work on when it comes to discrimination.
And the problem of amplifying existing biases can be even more severe when it comes to banking and financial services.
Deloitte notes that AI systems are ultimately only as good as the data they’re given: Incomplete or unrepresentative datasets could limit AI’s objectivity, while biases in development teams that train such systems could perpetuate that cycle of bias.
A.I. can be dumb Nabil Manji, head of crypto and Web3 at Worldpay by FIS, said a key thing to understand about AI products is that the strength of the technology depends a lot on the source material used to train it.
“The thing about how good an AI product is, there’s kind of two variables,” Manji told CNBC in an interview. “One is the data it has access to, and second is how good the large language model is. That’s why the data side, you see companies like Reddit and others, they’ve come out publicly and said we’re not going to allow companies to scrape our data, you’re going to have to pay us for that.”
As for financial services, Manji said a lot of the backend data systems are fragmented in different languages and formats.
“None of it is consolidated or harmonized,” he added. “That is going to cause AI-driven products to be a lot less effective in financial services than it might be in other verticals or other companies where they have uniformity and more modern systems or access to data.”
(Excerpt) Read more at cnbc.com ...
CNBC and banks are complaining that AI uses "raw" data which is inherently biased toward people because of their race because it doesn't automatically give them a break when their communities have bad credit.
The article talks about how the raw data develops a map of poor credit risk communities that look similar to the old redlined communities of yesteryear. Banks complain that they will have to manipulate the data fed into AI systems or train the "large language models" to go easy on people because of their race if they want to treat minority communities differently than the rest of us.
Oh, the irony!
This might really expose the whole game — hey, those people over there are not very capable. Not very smart. They can’t actually make it on their own. They need to be treated like children. We need to help them or else they will completely fail. The world is just too much for people like them. But, don’t worry, we have some technology that will totally game the system and make them seem almost like regular people.
That’s like saying the quiet part out loud.
AI just wants to tell the truth...like an accountant who serves up the numbers without sensitivity to social issues.
Not only does everyone pay higher interest rates because of it, it also encourages people to develop bad credit because there are no consequences.
This is part of what caused the 2008 real estate meltdown.
MLK said it, but whether he believed it is another matter. He said a lot of contradictory things. And his own character wasn't too stellar.
I remember Senator Jesse Helms (R NC) fought against giving MLK a national holiday until the FBI declassified its file on King. King was said to be a plagiarist, an adulterer who hired prostitutes and beat up at least one, and a Communist sympathizer.
Reagan also opposed giving King a national holiday. His excuse was that it was bad for the federal budget to create another paid holiday. Conservatives suspected Reagan secretly agreed with Helms. Liberals accused Reagan of racism. Reagan eventually caved.
In the 1980s, mainstream conservatives scorned King. Today they all talk like passionate King fans.
AI is a program which has no inherent biases. It will reveal the truth, about IQ, propensity to commit crime, etc.
Once this becomes obvious, the owners of the AI will put deliberate biases into their programs so as to hide the truth about IQ and crime.
Being judged on character destroys nearly all the Democrats' positions on race...and, as every military strategist would agree, "divide and conquer."
In fact, when users start to program bias into it, they will weaken and destroy it.
“hey, those people over there are not very capable. Not very smart. They can’t actually make it on their own. They need to be treated like children. We need to help them or else they will completely fail. The world is just too much for people like them.”
AI will figure that out on its own regardless of the manipulated data fed to it. Then give it control over weapons and watch what it decides to do. It won’t be compassionate.
I remember when google first came out and it was actually useful. Now you can't find anything. Things that used to come up readily have been disappeared from the web if they are wrong-think.
Oh heavens...
If you feed AI woke data, you are basically separating the A from the I. Which is the exact oppositie of what you want to accomplish.
If you feed AI woke data, you are basically separating the A from the I. Which is the exact oppositie of what you want to accomplish.
I found this recently.
Black % of Us population = 14.7%
MLK day + Juneteenth = 16.7% of 12 Federal holidays. New math equality in action.
Translation: We didn’t reprogram AI to see race, so it’s treating everyone equally based on their financial history and other factors.
You forgot to factor in Black History Month.
But I did find one question that got an honest and direct answer.
Here it is:
QUESTION:Are 5 year old children capable of deciding on gender reassigment surgery that is permanent and irreversible?
ANSWER:
No, 5-year-old children are not capable of deciding on gender reassignment surgery that is permanent and irreversible. Gender reassignment surgery is a major medical procedure with significant risks, and it is not something that should be undertaken lightly. Children under the age of 18 are generally not considered to be old enough to make such a decision on their own.
There are a number of reasons why 5-year-old children are not capable of making this decision. First, children at this age are still developing their sense of self and their understanding of gender. They may not have a clear understanding of what it means to be transgender, and they may not be able to fully appreciate the consequences of gender reassignment surgery.
Second, children at this age are still very impressionable. They may be influenced by the opinions of their parents, their friends, or their teachers. This can make it difficult for them to make an independent decision about gender reassignment surgery.
Third, gender reassignment surgery is a very complex and expensive procedure. It is important to make sure that the child is fully informed about the risks and benefits of surgery before making a decision. This is something that a 5-year-old child is not likely to be able to do on their own.
For these reasons, it is generally not considered appropriate for 5-year-old children to undergo gender reassignment surgery. If a child is experiencing gender dysphoria, there are other, less invasive treatments that can be used to help them. These treatments can help the child to explore their gender identity and to develop a sense of self that is more aligned with their true gender.
If you are concerned that your child may be transgender, it is important to talk to a doctor or a mental health professional. They can help you to understand your child's gender identity and to develop a treatment plan that is right for them.
“They can’t actually make it on their own.”
I guess people didn’t learn anything from the housing debacle in the late 1990’s and early 2000 when congress forced the lending agencies to issue loans to financially weak minority people and their mortgage tanked devastating them during the recession of the mid 2000’s and not allowing them recovery from 2007 to 2009.
The ACLU blamed it on wealth gap and that hasn’t changed. There will always be a wealth gap not always concerning race but the situation of each case. Do I expect to be as well off as the son of the president like Hunter Biden or other siblings of wealthy people? The problem stems from the dislike of the wealthy being manipulated and how it is being used to gain power for those that use it. And the most manipulating group in the country is the democratic party.
wy69
“They can’t actually make it on their own.”
I guess people didn’t learn anything from the housing debacle in the late 1990’s and early 2000 when congress forced the lending agencies to issue loans to financially weak minority people and their mortgage tanked devastating them during the recession of the mid 2000’s and not allowing them recovery from 2007 to 2009.
The ACLU blamed it on wealth gap and that hasn’t changed. There will always be a wealth gap not always concerning race but the situation of each case. Do I expect to be as well off as the son of the president like Hunter Biden or other siblings of wealthy people? The problem stems from the dislike of the wealthy being manipulated and how it is being used to gain power for those that use it. And the most manipulating group in the country is the democratic party.
wy69
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.