SPOILER ALERT! In the following text, I will discuss some details about the 2011 movie Limitless. If you haven't seen the movie and don't want to get spoiled, I recommend watching it first and then reading this.
Let's get started!
Since the emergence of LLMs, we have all started pondering questions like "When will AGI arrive?" and "How will this technology reshape our lives?" But of course, the first question that comes to mind is: "If we had a very intelligent machine, what would we do with it first?"
You might remember the 2011 movie Limitless starring Bradley Cooper. The movie is essentially based on the "Ten percent of the brain myth" It tells the story of Eddie, who, after encountering his ex-brother-in-law and taking the mysterious NZT-48 pill (which could be a catchy name for a large language model) from him, begins to use 100% of his brain instead of just 10%. This results in Eddie suddenly becoming very intelligent, leading to a series of crazy events. You might be wondering, what does this movie have to do with AI?
In my opinion, Limitless sheds light on how LLMs have impacted companies, ventures, the market, and people so far, and what future impacts they might have. If NZT-48 were real and you had access to it, what would you do? This question is quite similar to asking, "If you had a very intelligent machine, how would you use it?" So, let's take a look at what Eddie did in the movie.
1. Fixing Relationships with His Landlord
The first thing Eddie does under the influence of the pill is mastering communication skills. Not only does he manage to calm his angry landlord, but he also helps her with her law assignment and quickly ends up in bed with her. Interestingly, the initial entry of LLMs into our lives was through generating more effective and sophisticated emails, writing essays, customer service via chatbots, and Q&A assistants. In short, day-to-day communication. An interesting coincidence, isn’t it?
2. Cleaning His Apartment
The next thing Eddie does is cleaning his messy and dirty apartment. In a sense, NZT-48 functions as a productivity and project management tool.
3. Writing His Book in Hours
Eddie, a struggling science fiction writer, manages to write the book he couldn't touch for months in just a few hours under the influence of NZT-48 and sends it to his editor. If you recall, one of the first steps of transformer technology was generative art... Still think it's a coincidence?
4. Improving His Image
After getting his basic affairs in order, the first thing Eddie does is improve his appearance and adopt a better style. This is similar to how people in real life enhance their photos with AI filters and create avatars with AI.
5. Learning New Languages
One of the most impressive scenes in the movie is Eddie's ability to learn different languages in just a few hours and speak them with a perfect accent, greatly impressing those around him.
6. Quickly Learning and Remembering All Information
Under the influence of NZT-48, Eddie can instantly recall tiny bits of information he learned years ago and quickly learn anything.
7. NZT-48 is Addictive
Of course, the effect of NZT-48 wears off when not used. Everyone who uses this pill becomes instantly addicted, and once you stop, you're ruined. It seems intelligence is addictive.
8. Entering the Stock Market to Grow His Money
Realizing he needs to quickly increase his capital, Eddie’s first thought is to enter the stock market and grow his money. And he succeeds very well in this (unlike in real life).
9. Trying to Access More NZT-48
NZT-48 is an expensive and hard-to-find product. Eddie soon realizes that his limited supply of NZT-48 will run out and takes measures to prevent this. He reverse engineers NZT-48 and starts producing it himself.
10. Consulting for Big Firms
Big whales in the market notice Eddie's rapid rise and start paying him enormous fees for consultancy.
11. Rivals Emerge and Other NZT-48 Users Try to Hunt Him
Of course, you can’t be the only one desiring such an amazing thing. Others who learn about NZT-48, like Eddie, reach out to him to eliminate him and seize his supply of NZT-48. One of these people is even one of the big whales Eddie consults for. They shut down the labs where Eddie has NZT-48 produced and try to become a monopoly.
12. Modifying the Formula and Making It More Efficient
Later, as competition increases in the market, Eddie uses the technology itself, delving into its core to create new innovations. He improves the formula of NZT-48, eliminating its side effects and problems. The formula reaches a point where he no longer needs to take pills continuously. In the final scene, they have the following conversation:
Carl Van Loon : You're no longer equipped to fight me.
Eddie Morra : I may be off it, but you think I didn't learn anything? That my synapses didn't change? That I kept absolutely nothing? I see everything, Carl. I'm 50 moves ahead of you and everybody else.
13. Running for Senate
This last part of the movie is a bit scary, to be honest. Eddie concludes that the best thing he can do with this power is to enter politics. He aims to become the President of the United States one day, thinking this is the highest power he can reach.
Looking back at what we have discussed, you might notice how similar NZT-48 is to LLMs made possible by Transformers technology.
Some Observations:
Obv. 1. Most ideas are not original
99% of the products created using LLMs are not based on original ideas. Just like Eddie in the movie, the market first tries to grab the low-hanging fruits. For example, creating stock market applications is an idea that almost everyone has (many people tried to create portfolio management AIs even before LLMs). Even getting LLMs to write code is an obvious idea (see what Eddie did at step-12). It seems that everyone has similar thoughts about what can be done with a high intelligence at their command.
Obv. 2. LLMs have limitations, just like NZT-48
Although LLM is an impressive technology, it has some limitations, just like NZT-48. The most advanced models are pretty expensive when used at scale, they're slow, they tend to grow on your data, and they have a lot of latency. Therefore, chip manufacturers need to focus on producing solutions that allow LLMs to run on-device. Only in this way they can be cheap, fast, and low-latency. Additionally, dependence on large monopolies can only be reduced in this way.
Obv. 3. Unlike NZT-48, LLM is not a magic pill that enhances general intelligence
Besides obvious issues like context window length and hallucination, we also cannot say that LLMs are a solution for general intelligence.
If we draw an analogy between LLMs and the human brain, we can say that it resembles the human speech lobe. Transformers, more generally, mimic the generative functions of humans. When you try to imagine something you just saw by closing your eyes, your imagination does not match exactly what you saw, but as you can reconstruct the important parts in your mind's eye or generate derivatives of what you saw, transformer-based systems can achieve something similar.
Humans usually select grammar or the next word without conscious thought while producing speech. We do this very quickly thanks to probabilistic machines embedded in our heads. In our first year of life, we progress from being unable to speak to forming basic speech just by listening to the conversations around us. Sophisticated speech develops over years. The advantage of LLMs is that they are trained with very large and sophisticated speech (text) datasets in many different languages. When they synthesize speech based on this dataset, it is normal to see that reflections of reasoning, rational thinking, and logic will appear in the synthesized speech. This is because these sophisticated intelligence elements are embedded in the underlying dataset. I believe it is a mistake to attribute more meaning to LLMs than what the speech lobe does.
The Future of AI
Today, we have very good vision tools based on CNNs (and more transformer based vision models are on the way) and excellent speech-to-text and text-to-speech tools. Finally, LLMs have solved the issue of speech (text) generation. Personally, I think that the remaining advanced reasoning and planning tasks will be solved using AI Agents, knowledge graphs and logic graphs. Neuro-symbolic AI and Agentic AI seem to be the paths to progress at this point.
In my humble opinion, those who don't engage with these areas in AI are at risk of facing extreme competition in AI landscape. Based on my ten-year outlook, ventures focused on AI-first physical technologies (first principles) or accelerating physical techs' advancement and widespread adoption (that is what we do at Fabriforge), apart from those focused on cutting-edge areas of AI, are likely to achieve greater success.
Final Note
Even though Limitless is based on a false myth about the brain, it is a quite interesting movie. It almost perfectly outlines how the development of AI in the market would unfold and seems to have very good insights into the dilemmas of AI. Eddie's rapid success using NZT-48 serves as a metaphor for the disruptive potential of AI in business.
The movie underscores the importance of innovation and the ability to capitalize on new opportunities, which is crucial for AI ventures. As competition in the AI landscape intensifies, things are bound to get ugly. Businesses must develop unique applications that makes them "the-only", ensuring they can stand out and thrive.
Discuss
What are your thoughts on the parallels between Limitless and the AI? In which areas do you believe researchers and companies should focus their efforts to maximize AI's impact? Are there specific technologies or applications, like Neuro-Symbolic AI or Agentic AI, that you think hold the most promise? Let's share insights and ideas on how we can guide AI development for greater innovation and growth. Your perspectives and experiences are invaluable to this discussion!
If you found this discussion insightful and want to stay updated on my future posts in AI and tech, follow me on X and connect with me on LinkedIn. Also, don't forget to take your Omega-3 pills, they are the ones closest to NZT-48 😉
Top comments (2)
This movie should be call "Secret Life of Eddie Morra" 😀
Why somehow I am thinking Elon is also secretly working on NZT-48 tho? 🤔