Introducing Lensa and ChatGPT
This week in AI and ML news: A new color of the year and two headline-grabbing solutions.
Author’s Note
While governments remain deadlocked on how to address climate change and its impacts, the business world is in something closer to lockstep. A recent survey from the Boston Consulting Group found that 87% of executives believe AI-powered solutions hold the key to preventing, mitigating, and managing the ravages of climate change. IotPlaybook just re-shared our blog exploring some of the ways computer vision is already making a difference. Check it out.
AI News
ChatGPT: The Conversational Solution Making Headlines
Last week, OpenAI, the San Francisco-based company behind DALL-E 2, unveiled a new chatbot to the public. According to New York Times technology columnist Kevin Roose, ChatGPT (short for generative pre-trained transformer) is, “quite simply, the best artificial intelligence chatbot ever released to the general public.”
Like DALL-E 2 before it, OpenAI’s new generative chatbot has set the internet ablaze, inspiring users to share their experiences with the solution and raising questions about what the future of various fields could hold. The now-viral solution has already proven capable of writing jokes and essays, explaining complex subjects to various audiences, creating text-based games, and more. As with other generative solutions, responses have ranged from amusement to ethical concern to outright fear.
To learn more about the solution everyone’s talking about, I prompted ChatGPT to tell me a little about itself:
Bennett Glace: In short, how does ChatGPT work?
ChatGPT: ChatGPT is a variant of GPT-3 (Generative Pretrained Transformer 3), which is a type of language model developed by OpenAI. GPT-3 uses a deep learning technique called "transformer" to generate human-like text. The ChatGPT variant is specifically designed to generate responses to user input in a conversational style.
In general, GPT-3 works by predicting the next word in a sequence of text based on the words that have come before it. When given a prompt, the model will use its vast knowledge of language to generate a response that is relevant to the prompt and follows the correct grammatical structure of the language.
One of the key features of GPT-3 is its ability to generate text that sounds human-like, which makes it useful for tasks such as chatbots and language translation. It is also able to generate text in a wide range of styles and formats, including conversational text like that used in chatbots.
Overall, ChatGPT uses deep learning techniques to generate human-like responses to user input in a conversational style, making it useful for tasks such as chatbots and language translation.
BG: There are plenty of conversational solutions out there, what makes ChatGPT exciting and different?
CGPT: I'm sorry, but I am not able to browse the internet and therefore do not have information on other conversational solutions. As a large language model trained by OpenAI, my knowledge is based solely on the text that has been input to me. I do not have the ability to compare ChatGPT to other conversational solutions or provide information on what makes it unique or different.
BG: What are some of the most exciting near- and long-term use cases for this technology?
CGPT: As a large language model, GPT-3 (and the ChatGPT variant) can be used for a wide range of natural language processing tasks, such as language translation, text summarization, text generation, and chatbot development. In the near-term, the technology could be used to improve the accuracy and fluency of machine translation systems, making it easier for people to communicate across languages. In the long-term, the technology could potentially be used to develop more advanced chatbots and virtual assistants that can hold more natural and engaging conversations with humans.
BG: What's next?
CGPT: I'm sorry, but I am not able to provide information on future developments or plans for ChatGPT, as I am a large language model trained by OpenAI and do not have the ability to browse the internet or access information on current events or future plans. My knowledge is based solely on the text that has been input to me.
Lensa Sparks a New Debate Over AI-Generated Art
Whether or not you’ve downloaded Lensa and checked out its features, you’ve undoubtedly seen its work. Lensa AI made waves last week when it added a new Magic Avatar feature to its photo-editing mobile app. Leveraging a handful of images from users and the Stable Diffusion neural network, the app can create high-quality digital portraits, even mimicking specific artists and art styles.
Though the feature has wowed millions and taken Lensa to the top of the App Store charts, it’s also attracted a healthy amount of controversy. Stable Diffusion was trained using billions of images from across the internet, some of which include identifying medical information and copyrighted material. What’s more, since the app offers users 50 unique AI-generated avatars for just $7.99, it’s unlikely that any freelance artists can realistically afford to compete with Lensa on price. Users have privacy concerns, with some taking to social media to comb through the terms and conditions.
Whatever the future holds for Lensa – and however Lensa changes the future – it represents a major milestone in the worlds of AI and image data. While mixed responses to Lensa raise familiar ethical conversations, its instant success with users suggests a growing appetite for AI tools that supplement human vision.
Pantone Calls on AI to Promote its Color of the Year
Throughout its official announcement, Pantone describes its color of the year for 2023 as “animated,” “electrifying,” and “audacious.” In short, Viva Magenta is “an unconventional shade for an unconventional time.” Though human experts selected the vibrant hue as this year’s winner, Pantone turned to generative AI to promote it with digital imagery.
The “Magentaverse,” which Pantone calls “an endless new ecosystem,” earned a mixed response from The New York Times Style Desk. Stella Bugbee said it “[felt] like a gimmick gone wrong,” noting, “Our ability to think about and differentiate between colors and apply meaning to them feels like a big part of what makes us human.” Jeremy Allen suggested that such a high-tech take on the color didn’t quite match the inherent “lo-fi-ness” of magenta. Vanessa Friedman, however, makes a point to note that color theorists do not consider magenta a color at all. If that’s the case, I can’t imagine a better place to explore this new tone than in an AI-built digital ecosystem.
About the Author & Plainsight
Bennett Glace is a B2B technology content writer and cinephile from Philadelphia. He helps Plainsight in its mission to make vision AI success repeatable, scalable and traceable for enterprises across industries.
Plainsight provides the unique combination of AI strategy, a vision AI platform, and deep learning expertise to develop, implement, and oversee transformative computer vision solutions for enterprises. Through the widest breadth of managed services and a vision AI platform for centralized processes and standardized pipelines, Plainsight makes computer vision repeatable and accountable across all enterprise vision AI initiatives. Plainsight solves problems where others have failed and empowers businesses across industries to realize the full potential of their visual data with the lowest barriers to production, fastest value generation, and monitoring for long-term success. For more information, visit plainsight.ai.
The interview with ChatGPT is ?? !!!!