Future Today #095 - GPT-4. Google. Microsoft. Midjourney. OpenAI

Welcome to Future Today! A newsletter for those curious about social innovation, disruptive technologies and futures studies. In it I share weekly articles, reports and interesting links, and recommendations of books, movies, series, events and courses.

🤖 A lot has happened this week with Generative Artificial Intelligences, so today's newsletter will be dedicated to them. Future Today GenAI special!

💡 FTI 2023 Trend Reports. Downloaded more than a million times every year, FTI's annual technology trends report is a must read for all industries. This year, as in the previous year, they have divided the report into different topics and one of them is Artificial Intelligence where they include key techniques and influential models and more than 100 AI trends related to the enterprise, consumer ecosystem and government.

💥 A new era for AI and Google Workspace. For nearly 25 years, Google has built helpful products that people use every day — from Search and Maps, to Gmail and Docs in Google Workspace. AI has been transformational in building products that have earned a valued place in people’s lives. We’re now making it possible for Workspace users to harness the power of generative AI to create, connect, and collaborate like never before. To start, we’re introducing a first set of AI-powered writing features in Docs and Gmail to trusted testers.

💬 Introducing Microsoft 365 Copilot – your copilot for work. Today, we are bringing the power of next-generation AI to work. Introducing Microsoft 365 Copilot — your copilot for work. It combines the power of large language models (LLMs) with your data in the Microsoft Graph and the Microsoft 365 apps to turn your words into the most powerful productivity tool on the planet.

✨ GPT-4 is OpenAI’s most advanced system, producing safer and more useful responses. GPT-4 can solve difficult problems with greater accuracy, thanks to its broader general knowledge and problem solving abilities. GPT-4 is more creative and collaborative than ever before. It can generate, edit, and iterate with users on creative and technical writing tasks, such as composing songs, writing screenplays, or learning a user’s writing style.

💭 Microsoft just laid off one of its responsible AI teams. Microsoft laid off its entire ethics and society team within the artificial intelligence organization as part of recent layoffs that affected 10,000 employees across the company, Platformer has learned. The move leaves Microsoft without a dedicated team to ensure its AI principles are closely tied to product design at a time when the company is leading the charge to make AI tools available to the mainstream, current and former employees said.

Recommended tv series: Humans (2015 - 2018) // Recommended book: Superintelligence (2014) - Nick Bostrom 

🤖 The Generative AI Race Has a Dirty Secret. The race to build high-performance, AI-powered search engines is likely to require a dramatic rise in computing power, and with it a massive increase in the amount of energy that tech companies require and the amount of carbon they emit. “There are already huge resources involved in indexing and searching internet content, but the incorporation of AI requires a different kind of firepower,” says Alan Woodward, professor of cybersecurity at the University of Surrey in the UK.

🧠 How OpenAI is trying to make ChatGPT safer and less biased. Have you been threatened by an AI chatbot yet? Over the past week it seems like almost every news outlet has tried Microsoft’s Bing AI search and found that the chatbot makes up stupid and creepy stuff. It repeatedly told a New York Times tech columnist that it “loved” him, then claimed to be “offended” by a line of questioning in a mock interview with The Washington Post. In response, Microsoft has limited Bing to five replies per session in an effort to reduce the chances it goes off-piste.  

🕹️ An AI Learned to Play Atari 6,000 Times Faster by Reading the Instructions. Despite impressive progress, today’s AI models are very inefficient learners, taking huge amounts of time and data to solve problems humans pick up almost instantaneously. A new approach could drastically speed things up by getting AI to read instruction manuals before attempting a challenge.

💫 The new Midjourney V5 has been proposed so that we can't tell a real photo from a generated one (ES) Midjourney V5. According to its creators, the new engine features "much higher image quality, more diverse outputs, wider stylistic ranges, texture support, wider image formats, better image prompts, and wider dynamic range", among other improvements.

🇮🇸 How Iceland is using GPT-4 to preserve its language. On the initiative of the country’s President, HE Guðni Th. Jóhannesson, and with the help of private industry, Iceland has partnered with OpenAI to use GPT-4 in the preservation effort of the Icelandic language—and to turn a defensive position into an opportunity to innovate. The partnership was envisioned not only as a way to boost GPT-4’s ability to service a new corner of the world, but also as a step towards creating resources that could serve to promote the preservation of other low-resource languages.

Asking ChatGPT

🧔🏻 What is general intelligence or superintelligence?

🤖 General intelligence refers to the ability of an entity, whether human or machine, to perform a wide variety of complex cognitive tasks and adapt to new environments and situations effectively. In other words, general intelligence involves having a wide range of cognitive skills, such as abstract reasoning, problem solving, creativity, memory, language comprehension and decision making.

🤖 Superintelligence, on the other hand, refers to an intelligence that greatly exceeds human intelligence and is capable of performing tasks that humans would consider impossible. An entity with superintelligence could solve extremely complex problems, generate innovative ideas, and learn and adapt to new situations with unmatched speed and efficiency. It is expected that superintelligence will one day be achieved by highly advanced machines or artificial intelligence systems and will have significant implications for the way we live and work.

🧔🏻 Do you think we will reach artificial superintelligence?

🤖 As a language model, I have no beliefs as I do not have the ability to believe or have a personal opinion. However, I can say that many experts in the field of artificial intelligence believe that we will eventually reach artificial superintelligence.

🤖 Artificial superintelligence refers to an AI that is significantly more intelligent than humans in all cognitive areas. Currently, AI is advancing at a rapid pace and significant advances are being made in areas such as machine learning and natural language processing. As technology continues to improve, some experts believe that we will reach an era where machines will surpass human intelligence.

🤖 However, there are debates about whether artificial superintelligence would be beneficial or detrimental to humanity. Some argue that it could be the key to solving many of the world's biggest problems, such as disease, poverty and climate change. Others fear that artificial superintelligence could be dangerous if not properly controlled, and it may be difficult to predict how superintelligent AI might act if it gets out of control.

As more and more artificial intelligence is entering into the world, more and more emotional intelligence must enter into leadership - Amit Ray

If you liked it... Share it! Don't be shy! And subscribe! If you want to get in touch with me, ping me at alayon.david@gmail.com. See you in two weeks! 🤓

📌 Read the newsletter in Spanish