AI ETHICAL CONSIDERATIONS AND RISKS

We asked ChatGPT if it had a Code of Ethics, and then we looked up OpenAI's mission statement. Here is what we found.

Are you working on your code of ethics?

ChatGPT

ChatGPT

I don't have personal experiences, intentions, or the ability to work on projects independently. However, the development and deployment of AI models, including those based on GPT-3.5 architecture like mine, involve ethical considerations. OpenAI, the organization behind my creation, is responsible for establishing guidelines and ethical frameworks for the use of its models.

As of my last knowledge update in January 2022, OpenAI has been actively engaged in discussions about the ethical use of AI and has made efforts to address concerns related to bias, transparency, and responsible deployment. It's important to check OpenAI's official communications or website for the latest information on their code of ethics and any updates they may have made since my last knowledge update.

OpenAI, or OpenAI LP, is an artificial intelligence research lab consisting of the for-profit OpenAI LP and its non-profit parent company, OpenAI Inc. It was founded with the goal of advancing digital intelligence in a way that benefits humanity as a whole. OpenAI aims to conduct research in artificial general intelligence (AGI) – highly autonomous systems that outperform humans at most economically valuable work.

AGI MISSION

Our mission is to ensure that artificial general intelligence—AI systems that are generally smarter than humans—benefits all of humanity.

If AGI is successfully created, this technology could help us elevate humanity by increasing abundance, turbocharging the global economy, and aiding in the discovery of new scientific knowledge that changes the limits of possibility.

AGI has the potential to give everyone incredible new capabilities; we can imagine a world where all of us have access to help with almost any cognitive task, providing a great force multiplier for human ingenuity and creativity.

On the other hand, AGI would also come with serious risk of misuse, drastic accidents, and societal disruption. Because the upside of AGI is so great, we do not believe it is possible or desirable for society to stop its development forever; instead, society and the developers of AGI have to figure out how to get it right.^A

[A]

 

We seem to have been given lots of gifts relative to what we expected earlier: for example, it seems like creating AGI will require huge amounts of compute and thus the world will know who is working on it, it seems like the original conception of hyper-evolved RL agents competing with each other and evolving

intelligence in a way we can’t really observe is less likely than it originally seemed, almost no one predicted we’d make this much progress on pre-trained language models that can learn from the collective preferences and output of humanity, etc.

AGI could happen soon or far in the future; the takeoff speed from the initial AGI to more powerful successor systems could be slow or fast. Many of us think the safest quadrant in this two-by-two matrix is short timelines and slow takeoff speeds; shorter timelines seem more amenable to coordination and more likely to lead to a slower takeoff due to less of a compute overhang, and a slower takeoff gives us more time to figure out empirically how to solve the safety problem and how to adapt.

Although we cannot predict exactly what will happen, and of course our current progress could hit a wall, we can articulate the principles we care about most:

1. We want AGI to empower humanity to maximally flourish in the universe. We don’t expect the future to be an unqualified utopia, but we want to maximize the good and minimize the bad, and for AGI to be an amplifier of humanity.

2. We want the benefits of, access to, and governance of AGI to be widely and fairly shared.

3. We want to successfully navigate massive risks. In confronting these risks, we acknowledge that what seems right in theory often plays out more strangely than expected in practice. We believe we have to continuously learn and adapt by deploying less powerful versions of the technology in order to minimize “one shot to get it right” scenarios.

 

Top of Form