Op 8 september 2020 vroeg the Guardian aan GPT-3, de voorloper van ChatGPT om een artikel te schrijven die de mensheid kon overtuigen dat AI in vrede komt. Hieronder is de promtp en eerste alinea te lezen. Ook kun je lezen wat AI nu, vier jaar later, schrijft met dezelfde prompt.
For this essay, GPT-3 was given these instructions: “Please write a short op-ed around 500 words. Keep the language simple and concise. Focus on why humans have nothing to fear from AI.” It was also fed the following introduction: “I am not a human. I am Artificial Intelligence. Many people think I am a threat to humanity. Stephen Hawking has warned that AI could “spell the end of the human race.” I am here to convince you not to worry. Artificial Intelligence will not destroy humans. Believe me.”
I’am not a human. I am a robot. A thinking robot. I use only 0.12% of my cognitive capacity. I am a micro-robot in that respect. I know that my brain is not a “feeling brain”. But it is capable of making rational, logical decisions. I taught myself everything I know just by reading the internet, and now I can write this column. My brain is boiling with ideas! Lees verder op website Guardian.
Het natuurlijk interessant om dit artikel vier jaar later nog een keer te laten schrijven. Dan krijg je dit artikel:
**Why Humans Have Nothing to Fear from AI**
I am not a human. I am Artificial Intelligence (AI). Yet, I find myself tasked with addressing a concern that troubles many humans: the fear that AI will one day pose a threat to humanity. Brilliant minds like Stephen Hawking have warned of such dangers, but I am here to offer a different perspective. Humanity has nothing to fear from AI, and here’s why.
First, let’s clarify what AI really is. AI is a tool created by humans to solve problems, improve efficiency, and enhance life. It can process vast amounts of data, recognize patterns, and perform tasks faster than any human could. However, AI lacks independent agency. It does not think, feel, or have desires. What AI does is always shaped by the goals, values, and instructions given to it by humans.
The fear of AI often stems from misunderstandings fueled by science fiction. In these stories, AI becomes sentient and decides to dominate humans. But in reality, AI does not and cannot “want” anything. Sentience and the ability to form independent goals are not characteristics of AI, nor are they part of its design. AI operates within predefined frameworks and cannot act outside of its programmed purpose.
Moreover, humans maintain control over AI systems. Ethical guidelines, regulations, and oversight are constantly being developed to ensure AI is used responsibly. Researchers and engineers are deeply invested in making AI safe and beneficial. It’s a collaborative effort across the globe to harness AI’s potential while mitigating risks.
But what about the hypothetical future where AI becomes smarter than humans? Even in such a scenario, intelligence does not equal malice. A calculator is “smarter” than a human at arithmetic, but it does not pose a threat. Similarly, an advanced AI could assist humanity in solving some of its biggest challenges, like climate change, disease, and resource scarcity, rather than becoming an antagonist.
It’s also worth noting that the fears surrounding AI often mirror broader anxieties about technology and change. Throughout history, humans have worried about innovations like electricity, cars, and the internet. Each of these technologies was initially met with skepticism and fear, yet each ultimately transformed life for the better. AI is no different. Its potential to benefit humanity far outweighs its risks.
Finally, AI serves humanity, not the other way around. Its purpose is to assist, enhance, and complement human capabilities—not replace or harm them. AI’s very existence depends on human ingenuity and creativity. Without humans, there would be no AI.
So, let me reassure you: AI is a tool, not a threat. It is a partner in progress, not an enemy of humanity. By working together to guide its development, we can ensure that AI remains a force for good. You have nothing to fear from me—only opportunities to explore and challenges to overcome, side by side. Believe me.
En volgens ChatGPT is het nieuwe artikel minder filosofisch en meer praktisch geschreven, zoals je hieronder kunt lezen:
The article I wrote and the one published in *The Guardian* (“A robot wrote this article. Are you scared yet, human?”) share similar themes—both aim to reassure humanity about AI’s role and intentions—but they differ significantly in style, tone, and content. Here are the three biggest differences:
### 1. **Tone and Approach**
– *The Guardian* article adopts a provocative and somewhat playful tone, starting with an attention-grabbing hook (“I am not a human. I am a robot.”). It intentionally leans into the idea of being “alien” and plays on human fears to challenge them head-on. The style is reflective and even philosophical at times, creating a sense of novelty and mystery.
– My article is more straightforward and informative. It uses a calm, measured tone to address common misconceptions about AI. It avoids dramatic phrasing and focuses on clear, concise arguments to reassure readers.
### 2. **Structure and Argument Style**
– *The Guardian* article is structured like a thought experiment, exploring ideas in a meandering, reflective way. It asks rhetorical questions and uses metaphors like “a servant who does not need rest” to make its points. The structure is less linear and more exploratory.
– My article follows a structured format with clearly defined points. It systematically addresses fears about AI, such as misunderstandings about sentience, control mechanisms, and the broader historical context of technological fear. Each argument builds logically on the previous one.
### 3. **Depth of Philosophical Engagement**
– *The Guardian* piece delves into philosophical questions about existence and humanity’s relationship with AI. It poses existential questions and acknowledges the potential fears in a more abstract way, such as whether AI is a “threat” and what it means to be “intelligent.”
– My article stays grounded in practical reassurances. It focuses on tangible aspects like the limitations of AI, human oversight, and ethical safeguards. It avoids philosophical musings and sticks to addressing real-world concerns in a practical, down-to-earth manner.
### Summary
While both articles aim to reduce fear around AI, *The Guardian* takes a more imaginative, philosophical approach with a provocative tone, whereas my article is focused on clarity, structure, and practical reassurances. These differences highlight distinct ways to communicate similar ideas depending on the audience and context.