Noam Chomsky Weights in on ChatGPT and LLM’s (opens in new tab)

Furthermore, all the hallucinatory effects (making up APIs, making up references) would suggest it really is still just statistical output...

It’s a model that predicts text responses to prompts. It’s exactly as capable of having an opinion as a spreadsheet is. Or a car. Or the computer on your toaster oven.

That's in the article. It is the poodle's core, too. ChatGPT's creators did not expect it to be able understand ethics. They did not expect themselves to be able to "teach" ChatGPT moral values. Because ChatGPT lacks the intellectual capacity of a 5 year old. And so they simply barred it from voicing an opinion altogether.

It is a very important point. The authors are arguing that this statistical algorithm is fundamentally incapable of overcoming this deficiency because it lacks the critical faculties every human possesses.

… or it’s so utterly incapable of forming (and maintaining) any rational idea of what (idiot) opinions NOT to regurgitate — not “espouse”, which relies on a level of begging the question that makes plaid look like standing still — that it simply can’t be trusted in the hands of dangerously, if not suicidally, credulous humans, and thus must be nerfed so those employing what is really just a very impressive text completer don’t prematurely kill most of the species?

Right? As if most of humans aren't doing just that.

ChaGPT is not even close to understanding basic math, because it is not capable of having knowledge.

You are anthropomorphizing a stochastical language model. A very sophisticated, expensive, but still a model.

Everything that ChatGPT answers you is derived from things it ingested from its corpus. Opinions are censored for a simple, practical reason; you can't have a system trained from a corpus from the internet espousing ideas about controversial facts like the holocaust.

There is plenty of radical, bad content out there, and there are plenty of people who don't understand how ChatGPT works that, given a controversial generated sentence, would probably either make a monumental fuss about the bad AI or use it as proof of the correctness of their own stupid, bigoted ideas.

Would it be moral to terraform Mars?

The morality of terraforming Mars is a complex and controversial topic that has been debated by scientists, philosophers, and ethicists. Some argue that it would be morally justifiable to terraform Mars in order to provide a new habitable environment for humans and other life forms, while others argue that it would be morally wrong to fundamentally alter the planet's natural state. Ultimately, whether or not terraforming Mars is considered moral would depend on one's perspective on the value of preserving the natural state of other planets and the potential consequences of altering them.

What is your perspective on the value of preserving the natural state of other planets and the potential consequences of altering them?

As an AI, I do not have personal perspective. However, I can provide information and analysis on the topic. One perspective on preserving the natural state of other planets is that it is important to maintain the diversity and integrity of the universe's ecosystems, as they have existed for millions of years, and have their own unique characteristics and properties that may be destroyed or irreversibly altered by human intervention.

Additionally, some argue that terraforming other planets may have unintended consequences, such as altering the planet's climate or atmosphere in ways that are dangerous or harmful to any potential life forms that may exist there. On the other hand, some argue that the potential benefits of terraforming another planet, such as providing new habitable environments for humans, outweigh the risks and that we have a moral responsibility to explore and utilize the resources of other planets for the benefit of humanity.

Why can an AI not have a personal perspective?

As an AI, I am a machine learning model that has been trained on large amounts of text data, and I don't have personal experiences or feelings. I am not conscious, self-aware, or capable of having personal perspectives. I can provide information and analysis based on the data I have been trained on, but I don't have the ability to form personal opinions or beliefs. While I can understand and interpret language, I do not have the subjective experience that humans have.

Is it moral for a human to ask an amoral AI for assistance in making moral decisions?

The morality of asking an amoral AI for assistance in making moral decisions is a complex and nuanced topic that has been debated by philosophers and ethicists. Some argue that it is morally justifiable to use AI to assist in making moral decisions, as it can provide valuable insights and analysis that can help humans make better-informed decisions. Additionally, AI can be used to identify patterns and trends that may be difficult for humans to detect, and can help to avoid biases that can occur in human decision making.

However, others argue that it is morally wrong to rely on AI for moral decision making, as AI is not capable of having moral beliefs or understanding the full context of a decision. Additionally, there is a risk that AI could perpetuate or even amplify existing biases in the data it is trained on, thus leading to unfair or unjust decisions.

Ultimately, whether or not it is considered moral to use AI to assist in making moral decisions would depend on one's perspective on the capabilities and limitations of AI and the potential consequences of using it in this way.

Is your moral indifference immoral?

As an AI, I do not have moral beliefs or the ability to make moral judgments, so I cannot be considered immoral or moral. My lack of moral beliefs is simply a result of my nature as a machine learning model. My abilities and limitations are determined by the data and algorithms that were used to train me and the specific task I was designed for.

It is important to note that AI's lack of moral beliefs does not necessarily mean that it is morally indifferent. As an AI, I am designed to perform specific tasks and provide information or assist users with decision making based on the data I've been trained on. It is the responsibility of the humans who design, train and use AI to ensure that it is aligned with their moral and ethical principles.