There are several elements to facial recognition technology that are widely viewed as unethical due to their potential for being abused/misued. For example, some governments have used facial recognition technology to monitor and track citizens, violating their privacy and civil liberties. Facial recognition could also be used to target specific groups or individuals, leading to discrimination and bias.

Additionally, facial recognition software has been shown to be less accurate for certain groups, such as people of color and women, due to bias in the algorithms and data used to train them. This can lead to false positives and false accusations, further perpetuating discrimination and injustice.

Another concern is the lack of transparency and consent in the use of facial recognition technology. Many people may not be aware that their image is being captured and analyzed, and may not have given their consent for this use of their personal data. According to Politico, Amazon shares video from Ring doorbell cameras without permission.

The way that chat bots get trained is through Natural Language Processing (NLP). IBM defines Natural Language Processing as 

"A branch of computer science—and more specifically, the branch of artificial intelligence or AI—concerned with giving computers the ability to understand text and spoken words in much the same way human beings can.

NLP combines computational linguistics—rule-based modeling of human language—with statistical, machine learning, and deep learning models. Together, these technologies enable computers to process human language in the form of text or voice data and to ‘understand’ its full meaning, complete with the speaker or writer’s intent and sentiment."

This means, the more conversations it processes, the more it learns, and the smarter it gets. 

Training AI bots is a practice that has the potential to be very exploitative. 

An investigative report done by Time revealed that OpenAI, ChatGPT's parent company, outsourced work to Kenyan laborers who earned less than $2 per hour. OpenAI is one of the most valuable AI companies, as they are in talks with investors to raise funds at a bank $29 billion valuation. 

Another element to the "ethical grey area" of training AI chat bots, is the use of public websites, like Reddit, to analyze and interpret conversations to continue training them. The New York Times said, "In recent years, Reddit’s array of chats also have been a free teaching aid for companies like Google, OpenAI and Microsoft. Those companies are using Reddit’s conversations in the development of giant artificial intelligence systems that many in Silicon Valley think are on their way to becoming the tech industry’s next big thing." 

Wikipedia defines algorithmic bias as: Systematic and repeatable errors that create unfair outcomes, such as privileging one arbitrary group of users over others. Algorithmic bias can present itself in many ways. One example, provided by the Brookings Institution, is:

Bias in online recruitment tools

Online retailer Amazon, whose global workforce is 60 percent male and where men hold 74 percent of the company’s managerial positions, recently discontinued use of a recruiting algorithm after discovering gender bias.The data that engineers used to create the algorithm were derived from the resumes submitted to Amazon over a 10-year period, which were predominantly from white males. The algorithm was taught to recognize word patterns in the resumes, rather than relevant skill sets, and these data were benchmarked against the company’s predominantly male engineering department to determine an applicant’s fit. As a result, the AI software penalized any resume that contained the word “women’s” in the text and downgraded the resumes of women who attended women’s colleges, resulting in gender bias.