Chat GPT Writing vs. Human Writing

Can Artificial Intelligence be bias on gender and race?

Sadly, the answer is yes. According to two articles, me and my partner read in STEM Skills, "Artificial Intelligence Has a Problem with Gender and Racial Bias. Here’s How to Solve It" by Joy Buolamwini and "Why algorithms can be racist and sexist" by Rebecca Heilweil, this is proven. 

"Artificial Intelligence Has a Problem with Gender and Racial Bias. Here’s How to Solve It" 

"This article, discusses problems with artificial intelligence in the workplace and how to combat these through inclusivity and addressing the current issues within technology. The biggest issue is the AI’s ability to recognize women over men, but especially, people of color. Some iconic people include Oprah Winfrey, Michelle Obama, and Serena Williams, who even through their popularity can’t be recognized by AI due to their darker complexion. The article stated problems with people of color having to use white masks to even be detected by the sensors. To solve the issue, they proposed increasing the awareness of the problem and advancing AI to where racial and gender bias aren’t factors within the system." - Lilah 

Chat GPT #1- Write at least a 100-word summary about artificial intelligence with gender and racial bias.

Artificial Intelligence (AI) has gained widespread attention and usage in various domains, but it is not without its flaws. One concerning issue is the presence of gender and racial bias within AI systems. Bias in AI refers to the unfair and discriminatory treatment or outcomes that can result from the algorithms and data used in training these systems. Due to the reliance on historical data that often reflects societal biases, AI models can perpetuate and amplify existing gender and racial disparities. For example, facial recognition algorithms have shown higher error rates for women and people of color, leading to potential discrimination in areas like law enforcement or hiring practices. 

Chat GPT #2 - Write a 100-word summary about the TIME article, Artificial Intelligence Has a Problem with Gender and Racial Bias. Here’s How to Solve It by Joy Buolamwini

In her article titled "Artificial Intelligence Has a Problem with Gender and Racial Bias. Here’s How to Solve It," written by Joy Buolamwini, the author highlights the issue of gender and racial bias in artificial intelligence (AI) systems and proposes potential solutions. Buolamwini emphasizes that AI algorithms can perpetuate discrimination and inequality due to biased training data and biased programming. She cites examples of facial recognition algorithms exhibiting higher error rates for women and people with darker skin tones. To address this problem, the author suggests four strategies: increasing transparency and accountability in AI development, ensuring diverse and inclusive teams in AI research and development, creating regulatory frameworks for auditing AI systems, and encouraging public engagement and education to raise awareness about the biases in AI and its impact on society.

"Why algorithms can be racist and sexist" 

"It perpetuates bias and discrim AI is relatively new, meaning we don't know everything about it. People tend to use AI because it's faster and more efficient. However, AI, like humans, is capable of being inaccurate and biased. Many artificial intelligence systems are vulnerable to algorithm bias. Algorithm bias is a collection of systematic and recurring flaws in a computer system that result in unfair results, such as preferring one racial group over another. There have been several cases of this. A few years ago, Amazon built a resume-screening tool.  The system had learned from the collected data that more resumes tended to originate from men and consequently discriminated against female applicants. New laws will need to be put into place to regulate AI and ensure no individual or group are discriminated against." - Gabi

Chat GPT #1 - Write at least a 100 word summary about this article (link was provided)

The article explores the issue of bias in algorithms, particularly in the context of facial recognition technology. It highlights how algorithms, which are trained on biased datasets, can reinforce and perpetuate societal biases, leading to discriminatory outcomes. The article emphasizes the need for transparency and accountability in algorithmic decision-making processes, urging for greater scrutiny and regulation to prevent algorithmic bias. It discusses ongoing efforts to address this issue, such as calls for algorithmic transparency, diverse dataset creation, and the development of ethical guidelines for algorithm design. Overall, the article underscores the importance of recognizing and addressing bias in algorithms to ensure fair and equitable outcomes.

Chat GPT #2 - In 100 words write a summary about this article that highlights the key ideas and points of the article (link was provided). 

The article explores the issue of bias in algorithms, particularly in facial recognition technology. It discusses how biased datasets used to train algorithms can perpetuate and amplify societal biases, leading to discriminatory outcomes. The article emphasizes the importance of transparency and accountability in algorithmic decision-making, advocating for greater scrutiny and regulation. It highlights the need for algorithmic transparency, diverse dataset creation, and ethical guidelines for algorithm design. The article concludes by stressing the significance of addressing algorithmic bias to ensure fair and equitable outcomes in society.

Based on what me and my partner, Gabi, came up with, I can ensure for the turing test that human and chat GPT writing is different. While sometimes it may be unnoticed, I believe with the right eye, you can tell the difference between a human and AI. In both the first and second article, the AI repeats itself: 

• To address this problem, the author suggests four strategies: increasing transparency and accountability in AI development...

• The article emphasizes the importance of transparency and accountability in algorithmic decision-making...

This is very important, as it signifies that there are two different articles about the same topic but from two different websites. While they may share a similar goal, AI still took the advantage to state the same thing that transparency and accountability in AI are important. The most apparent habit AI does that humans don't do as well is the pace. Humans can have thoughts that are similar in sophistication as AI, however, it may take them a while until they can fully form these ideas. To give an example of this, it's like how fast AI can write a college essay versus a human. Also, the word usage is key to really understanding how AI may think, specifically in the lack of empathy. AI's writing shows this through the anecdotes or even examples they give.