The first half is more destined to those who have yet to use generative AI on a regular basis – in all probability a shrinking crowd. Anyone who interacted with ChatGPT 3.5 and then 4 will have similar anecdotes. And while certainly useful, I found Ethan’s four principles to mix rules of thumb with prompting techniques and more general observations.

Part two I personally found of much greater interest, as Ethan delves into the implications for workers, demonstrating how they can learn to use AI to great effect, e.g. in creative work. Ethan dives deep into how gen-AI can produce efficiencies and superior results, but also lead to disaster if users get too comfy and “fall asleep at the wheel”. While several studies and research papers exist on these topics, it’s one of the first books that explains these concepts to laymen. It’s also enjoying to see him, rather than trying to dissect office jobs he may not be familiar with, instead humbly take himself as a guinea pig to explain in great minutiae how he wields this revolutionary tool in his work, at times using the very paragraphs we read as examples.

I found in several occasions echoes of my own book, e.g. when Ethan insists on how technology cannot be treated in a vat but goes hand in hand with frameworks and trends, thus how the way corporations have work organized is likely to change in serious ways, as it did in previous industrial revolutions. He too does not fall for the fallacy that because certain tasks in a job cannot be automated, the job is immune to disruption. He too notes the risks associated with a greater deployment of metrics and the diktat of data, what others have called “Digital Taylorism”, and alludes to what I termed being “pushed off of the sumo ring of cognition” by an AI that calls the shots.

He also takes a lucid and pragmatic approach to how such disruptive technology will be deployed in the workforce, detailing how employees use it covertly out of fear that their managers find out, though less convincing are his recommendations to leaders on how to instill a pro Gen-AI culture in the company – a pity given how this is fast becoming a concern for managers. A few other considerations also went neglected, like how those companies that fail to adapt will quickly fall behind those that do. But I feel this is also because he is primarily addressing employees, and that is nice to see in contrast to all the books guiding managers.

My favorite is his insistence that AI is proving most beneficial to juniors, who can boost their performance level to the vicinity of veterans; rather than concluding in the lines that “See, this is a great enhancement tool, not something that will eliminate jobs - so don't be afraid!”, or “it’s not AI that will displace workers, but the workers who master AI that will displace those who don’t” as the majority of so-called experts yell and parrot from every hilltop, he questions what implications this might have for seasoned workers, for those whose expertise becomes somewhat eroded and may no longer justify their wages. Following what I called the commoditization effect, AI could become a great equalizer, but (Duh!!) overall this will drag wages down. He notes how now some companies hire fresh graduates for jobs there where they used to hire people with at least five years of experience, because they can do practically just as well now with the help of AI.

Alas he also rightly note that expertise will still play a role, with solid arguments. But he dares not venture say how much of this expertise will still be required and how this will reshape companies - indeed, only time will tell. We could end up with a split of say 80% of juniors – or rather people paid with junior salaries – and only 20% of experts there where we had a more balanced split before, and such junior talent could be outsourced instead of employed, etc.

I pass on the final chapters on education and the future of AI, not for lack of interest but to avoid too long a commentary. Also great observations, for instance on how a future AI-mentor would be superior both for providing more constant feedback but also in its ability to take on several different roles (as opposed to the subjectivity of a single human coach, teacher or mentor). And here again there is the risk of overdependence, for instance (with his example of architect) consulting the AI on every single stroke.

All in all, a very good read that remains concise and echoes some of my concerns which I believe will only balloon with time as organizations reshape work.

Here's a refined and insightful book review based on your thoughts:

---

Ethan Mollick’s book serves as an excellent primer for those new to artificial intelligence, breaking down complex concepts into accessible insights. As someone who does not consider themselves an expert in AI, I found this book particularly helpful in demystifying key ideas and making them more understandable.

One of the highlights of the book is Mollick’s "Four Rules for Co-Intelligence," which offer a structured and thoughtful approach to engaging with AI. Rather than viewing AI as a replacement for human thinking, Mollick emphasizes its role as a tool that enhances our ability to create, analyze, and innovate. He also delves into the mechanisms behind AI—how it processes information, the sources it draws from, and the inherent biases that can shape its outputs. This discussion is crucial, as it encourages readers to approach AI with both curiosity and critical thinking.

What I found particularly compelling was Mollick’s perspective on AI in education. By allowing his students to use AI, he pushes them to think more deeply rather than simply outsourcing their work. This approach aligns with the broader theme of the book: AI is not just a technology to be feared or blindly accepted, but one to be understood and harnessed effectively.

For those unfamiliar with terms like GPT and large language models (LLMs), this book provides a solid foundation. It equips readers with the knowledge needed to make informed decisions about the benefits and risks of AI. Given the rapid advancement of this technology, Mollick’s insights are both timely and practical. Personally, reading this book has enhanced my own use of AI, giving me a clearer perspective on how to integrate it thoughtfully into my daily work.

Overall, this is a must-read for anyone looking to gain a foundational understanding of AI without getting lost in technical jargon. Whether you're a student, educator, or professional, Mollick’s balanced and insightful approach makes AI feel less intimidating and more like an opportunity to be explored.

This book offers a refreshingly balanced and thoughtful perspective on how AI will reshape our personal and professional lives without falling into either dystopian fear-mongering or blind techno-optimism. The author does an excellent job explaining complex AI concepts in accessible language while providing practical frameworks for adapting to an AI-integrated world. What I appreciated most was the focus on collaboration rather than replacement - showing how humans and AI can work together effectively rather than viewing it as a zero-sum competition. The real-world examples and case studies make the concepts tangible and immediately applicable to current workplace challenges. While some sections can feel a bit dense with information, overall it's an essential read for anyone looking to understand and thrive in our rapidly evolving technological landscape.

Excellent read. Written with deep thought and understanding of AI. Explains it very well at the same time. Super interesting!

The book feels like a sci-fi fantasy and there are a lot of interesting perspective on AI. Ethan Mollick paints a picture of AI as a fellow human being. This provides an interesting perspective where you can use AI as a tutor, coach, assistant and many other roles.

He also suggests to give specific role to AI as a prompting technique. For example, act as a marketing expert or act as an editor. This way of defining a role helps produce better results. He also mentioned about another technique, which is fascinating where you tell the AI to take a deep breath and answer step-by-step. Even though AI is not a human and doesn’t know how to breathe it surprisingly produced a superior result.

The book just gives you some perspective on how to use the AI, but it does not give you the exact prompts. You would have to do your own research and play around with different prompts. Ethan Mollick heavily emphasizes on experimentation and suggests us to play with AI then figure out its capabilities. At least I have figured out some capabilities, which surprised me. Now I have started using ChatGPT more frequently than before, after reading this book.

Given the remarkable nature of LLM's and their capture of our imaginations it was inevitable the business school perspective would come out. Co-Intelligence is a perspective on how to work with AI to improve productivity and the book highlights how in classroom (and professional settings) how these tools can be used to improve effectiveness, lead to inspiration as well as maintain competitive edge. For me I find looking into the technology engineering side more interesting but how to practically navigate these tools for greatest effect is in many ways much more important as the money required for the training of these models is only justified if they have a revenue stream and a revenue stream is only dependable if the userbase can monetize and this book can help you understand how to do that.

The author starts with the technology and its uniqueness and gives a framework of how to think about using technology for productivity enhancement. The book is mainly substantiated in Part II where the author how one can use AI with the chapters being AI as a person, creative, coworker, tutor, coach, our future, as us. Much of what goes into the book is the authors experience in teaching in business school with the students incrementally using these tools to improve their projects. The author shows how prompting can vastly affect the content, how being specific can deliver much more utility than making general requests and the variety of purposes that LLM's can be catered towards. One feels that from the snippets of prompts and responses, all of our expertise is at risk but simultaneously one feels all our productivity can be enhanced. This somewhat inescapably leads to the conclusion that we all need to start embedding the use of these tools in our work streams but not defaulting to copying and pasting results but rather squeezing narrow insights from these frameworks.

Overall the book is useful in explicitly showing how the tools could be seen to aid users differently based on how they used these tools reminding us that the tool itself doesn't have answers so much as the tool when properly used can extend ones expertise substantially. Nonetheless I would expect the content of the book to soon become outdated as new models are rolled out. I would like to think the main ideas/lessons will remain true, but the innovation in technology and these models does make one a little be weary to think that co-intelligence is a given rather than eventually a cause of labor substitution that will impact many people differently irrespective of whether they follow the advice.

"Co-Intelligence" by Ethan Mollick is a practical book that focuses on the use of AI, especially large language models (LLM). It provides examples and fundamental principles at a conceptual level, along with good practices for those interested in using LLMs to make better decisions and improve day-to-day work; This book would be a must-read for them.

He also presents four potential futures, exploring scenarios that speculate on the pace and traits of AI development; which reminds me of the four alternative futures scenarios archetypes by Jim Dator. But beyond scenarios, the key question here is: how fast and how capable will AI evolve? —which remains open, as there are many hypotheses but no concrete and definitive answers.

Mollick is one of the leading experts that seems to spend much time studying papers about and interacting with these tools. His perspectives and voice are highly recommended, even if you feel uncomfortable with what you hear.

The end of the book is particularly provocative. There, Mollick emphasizes the lack of sentient or human experiences within AI, underscoring its lack of "spark". He seems to make a distinction between 'intelligence' and 'mind', being a delightful food for thought.

This reminded me of Kasparov’s book, “Deep Thinking”, where he states that machines will never have purpose or imagination, qualities that make us unique as human beings…

Great introductory book on the subject for people who want to understand the basics of AI and it's basic implications on society and economy

Amazing book ! Genuinely nice to read and informative, I learned a lot about AI, what it is and what it’s definitely not.

brilliant book

Co-Intelligence doesn’t shout. It teaches. With a tone that’s grounded, encouraging, and refreshingly jargon-free, Ethan Mollick offers a roadmap for working with AI rather than reacting to it. Whether you’re experimenting as a creative, an educator, a small business owner, or simply trying to stay relevant, this book gives you the context and confidence to step in.

What resonated most with me was its practical, permission-giving approach: you don’t need to be technical, you just need to be curious. Mollick strips away the hype and fear and instead reframes AI as a tool for co-creation and thinking better. The examples are thoughtful, the strategies are accessible, and the mindset shift is real.

Great introduction to AI and how it impacts the whole society.

For last 2 years I heard a lot on Chat gpt and artificial intelligence..... this book gave them the 1st opportunity to understand LLM , what is LLM , their architecture, how they work and how we can leverage them in our life to be more productive... author very clearly explains how to use it as a companion and I clearly see a lot of uses ..... LLM once fully understood by the society in large will increase the level of transformation in the society and make humans more intelligent than what they are now.... he also explains various scenarios on how it will transform our life