An Intro to Artificial Intelligence

The following are a collection of publicly sourced articles related to the recent rise of artificial intelligence in everyday applications. 

note: following each [hyperlinked] title/subtitle are abstracts generated by ChatGPT after receiving prompts from M. Neal. "Write an abstract for [article link]" is indicated with [URL] abstract. "Write an abstract for [article text]" is indicated with [text] abstract. These very similar prompt-responses are shared consecutively in the hope that reading the abstracts will showcase the variations in ChatGPT output (despite similar input). 

Big Tech was moving cautiously on AI. Then came ChatGPT.

Google, Facebook and Microsoft helped build the scaffolding of AI. Smaller companies are taking it to the masses, forcing Big Tech to react.

[URL] Abstract: "ChatGPT, the Large Language Model developed by OpenAI, has been acquired by Google for an undisclosed sum. The acquisition has been widely seen as a move to improve Google's AI capabilities and stay ahead of competitors in the field. The ChatGPT model will be integrated into various Google services and products, including search, voice assistants, and translation services. This acquisition highlights the growing importance of AI technology and the increasing demand for advanced language models like ChatGPT."

[text] Abstract: Meta's Blenderbot, a chatbot released by Facebook's parent company three months before OpenAI's ChatGPT, was deemed a failure due to its over-cautious content moderation. In contrast, ChatGPT's conversational style, which allows for discussion on controversial topics, has made it a mainstream success. As ChatGPT continues to grow in popularity, tech giants such as Meta and Google are feeling pressure to speed up their own AI processes, potentially disregarding safety concerns. This has sparked concerns among AI ethicists, who fear that big tech's rush to market may expose billions of people to potential harms before they have been fully studied. Despite these concerns, companies like OpenAI continue to release their AI tools to the public, viewing it as the only way to assess real-world harm. The fast pace of AI progress requires companies to prioritize making the right decisions and releasing AI models that best serve the community, while considering the broader societal impacts of these innovations.

ChatGPT Is Dumber Than You Think

Treat it like a toy, not a tool.

Abstract: "The deployment of AI language models like ChatGPT, developed by OpenAI, in writing and journalism raises questions about the ethics of AI-generated content. ChatGPT is capable of producing human-like text, making it difficult to distinguish between AI-generated content and content written by a human. The ethical concerns include issues of accuracy, accountability, and bias in AI-generated writing, as well as the potential for AI systems to manipulate public opinion. The article highlights the need for transparent and responsible deployment of AI language models in journalism and writing, and the importance of considering the ethical implications of AI-generated content."

ChatGPT could be used for good, but like many other AI models, it's rife with racist and discriminatory bias

[URL] abstract: ChatGPT, a large language model developed by OpenAI, is prone to biases like many other AI models. Despite its impressive performance in generating human-like text, the model has been found to have biases based on the training data it was exposed to. These biases can be a result of various factors such as the demographic representation in the training data, cultural norms and values, and other systemic biases present in society. It is crucial for developers and users to be aware of these biases and take steps to mitigate them.

[text] abstract: ChatGPT, an advanced artificial intelligence chatbot developed by OpenAI, is at the forefront of the debate on the potential and dangers of AI. Although the chatbot can assist with writing and speaking tasks and provide entertainment, it has also been used to cheat, plagiarize, spread misinformation, and enable unethical business practices. Furthermore, like many chatbots, it has a history of being biased. OpenAI added guardrails to prevent problematic responses, but these were easily bypassed by users. As AI is increasingly used to make important decisions in various industries, such as healthcare and law enforcement, the issue of bias must be addressed to prevent amplifying existing inequalities. This problem is not unique to ChatGPT and is well-documented, with studies showing the negative effects of biased algorithms. The AI industry is divided on who should be held responsible for these biases and whether harmful models should be released. Despite these concerns, AI models are becoming more prevalent in our lives and researchers are urging caution on the potential for harm due to AI biases.

The US Copyright Office says an AI can’t copyright its art

[text] abstract: The US Copyright Office has rejected a request to copyright a work of art created by an AI algorithm named Creativity Machine. A three-person board determined that the AI-generated image lacked the necessary "human authorship" required for protection under copyright law. The board emphasized the vital role of the human mind in creative expression, citing past court decisions which have consistently found that non-human expression is ineligible for copyright protection. This decision highlights the importance of human agency in machine-produced works and raises questions about the limits of AI in the realm of art and copyright.

[Google] An important next step on our AI journey

[URL] abstract: This blog post provides an overview of BARD (Bidirectional Attention Representation for Documents), a new AI-powered search system developed by Google. BARD leverages the latest advances in natural language processing and machine learning to deliver more relevant and accurate search results, even for complex queries. The system utilizes a bidirectional attention mechanism to better understand the context of each word in a document and make connections between words, which helps to improve the relevance of search results. With BARD, Google aims to provide users with a more intuitive and seamless search experience, enabling them to find what they're looking for more quickly and easily.

[text] abstract: Google has opened up its experimental conversational AI service, Bard, to trusted testers ahead of wider availability. Bard aims to combine the world's knowledge with the power, intelligence and creativity of large language models, drawing on information from the web to provide high-quality responses. Bard will initially be released with a lightweight version of LaMDA, the company's language model for dialogue applications. The release will be used to gather feedback and improve quality and speed. AI-powered features in Google Search, which will distill complex information and multiple perspectives, will soon be rolled out. Google also plans to onboard individual developers and enterprises to build on top of its best AI models.