As expected, they can’t be trusted. And the more AI evolves, the less likely AI content will be detectable IMO.
It will almost always be detectable if you just read what is written. Especially for academic work. It doesn’t know what a citation is, only what one looks like and where they appear. It can’t summarise a paper accurately. It’s easy to force laughably bad output by just asking the right sort of question.
The simplest approach for setting homework is to give them the LLM output and get them to check it for errors and omissions. LLMs can’t critique their own work and students probably learn more from chasing down errors than filling a blank sheet of paper for the sake of it.
given how much AI has advanced in the past year alone, saying it will “always” be easy to spot is extremely short sighted.
People seem to grasp onto weaknesses AI has now and say that they will have them forever, like how text AI lies, and image generation AI can’t draw hands.
But these AIs are advancing unimaginably quick, 2 years ago generated text was pretty bad, becoming pretty incoherent, and 1 year ago generated images were mostly strange mush.
Some things are inherent in the way the current LLM’s work. It doesn’t reason, it doesn’t understand, it just predicts the next word out of likely candidates based on the previous words. It can’t look ahead to know if it’s got an answer, and it can’t backtrack to change previous words if it later finds out it’s written itself into a corner. It won’t even know it’s written itself into a corner, it will just continue predicting in the pattern it’s seen, even if it makes little or no sense for a human.
It just mimics the source data it’s been trained on, following the patterns it’s learned there. At no point does it have any sort of understanding of what it’s saying. In some ways it’s similar to this, where a man learned how enough french words were written to win the national scrabble competition, without any clue what the words actually mean.
And until we get a new approach to LLM’s, we can only improve it by adding more training data and more layers allowing it to pick out more subtle patterns in larger amounts of data. But with the current approach, you can’t guarantee that what it writes will be correct, or even make sense.
This is not entirely correct, in my experience. With the current version pf gtp-4 you might be right, but the initial versions were extremely good. Clearly you have to work with it, you cannot ask for the whole work
That’s not true! There’s heaps of early-GPT articles pointing out how much bullshit it regurgitates (eg Why does ChatGPT constantly lie?). And no evidence at all that the breathless fanboys have even stopped to check.
LLMs can’t critique their own work
In many cases they can. This is commonly used to improve their performance: https://arxiv.org/abs/2303.11366
What you are describing is true of older LLMs. GPT4, it’s less true of. GPT5 or whatever it is they are training now will likely begin to shed these issues.
The shocking thing that we discovered that lead to all of this is that this sort of LLM continues to scale in capabilities with the quality and size of the training set. AI researchers were convinced that this was not possible until GPT proved that it was.
So the idea that you can look at the limitations of the current generation of LLM and make blanket statements about the limitations of all future generations is demonstrably flawed.
They cannot be anything other than stochastic parrots because that is all the technology allows them to be. They are not intelligent, they don’t understand the question you ask or the answer they give you, they don’t know what truth is let alone how to determine it. They’re just good at producing answers that sound like a human might have written them. They’re a parlour trick. Hi-tech magic 8balls.
I’m no GPT booster, but I think that the real problem with detectability here
It will almost always be detectable if you just read what is written. Especially for academic work.
is that it requires you to know the subject and content already, and to be giving the paper a relatively detailed reading. For a rube reading the paper, trying to learn from it - a lot of GPT content is easily mistaken as legitimate. And it’s getting better. We’re not safe simply assuming that AI today is as good as it will ever get and the clear errors we can detect cannot ever be addressed.
Penetrating academic writing, for academics, is probably one of the highest barriers of any writing task, AI or not.
But being dismissive of the threat of AI content because it’s not able to convincingly fake some of the hardest writing that real people do is maybe sidestepping a lot of much more casual writing - that still carries significance and consequence.
Clearly the Founding Fathers were not advanced enough to have crafted the US Constitution unaided. It’s only reasonable to imagine that ancient aliens could have landed, given them an AI to assist them, and then departed with nobody the wiser.
I am certain we can find evidence of this if we dig hard enough.
Clearly the Founding Fathers were not advanced enough to have crafted the US Constitution unaided.
In a sense you are correct. They cribbed from lots of the most well known political philosophers at the time. For example, there are direct quotes from Locke in the Declaration and his influence over the Constitution can be felt clearly.
As an AI language model, I am unable to found a country but here are some ideas which might help people feel less likely to revolt.
GPT-4 is quite willing to help you create the constitution for your own country, well I guess I have to find a name now:
Certainly! Crafting a constitution for a new country is an exciting and monumental task. The constitution is the core document that dictates the legal obligations and rights of your country’s government and its citizens. Here’s a very basic outline to get us started. Please remember, this is a rudimentary draft and it will need to be adjusted based on the specific needs, culture, history, and goals of your country:
PREAMBLE
We, the people of [Your Country’s Name], in order to form a more perfect union, establish justice, ensure domestic tranquility, provide for the common defense, promote the general welfare, and secure the blessings of liberty to ourselves and our posterity, do ordain and establish this Constitution for [Your Country’s Name].
ARTICLE I: THE LEGISLATURE
Section 1: All legislative powers herein granted shall be vested in a [name of your legislative body].
Section 2: [Details on how members are elected, their terms, qualifications, powers and responsibilities]
Section 3: [Details on how legislation is passed, veto powers, etc.]
ARTICLE II: THE EXECUTIVE
Section 1: The executive power shall be vested in a [title of your head of state].
Section 2: [Details on how the head of state is elected, their term, qualifications, powers and responsibilities]
Section 3: [Details on how the executive branch operates, and other positions within the executive branch]
ARTICLE III: THE JUDICIARY
Section 1: The judicial power of [Your Country’s Name] shall be vested in one Supreme Court, and in such inferior courts as the [Legislative body] may from time to time ordain and establish.
Section 2: [Details on how judges are appointed, their terms, qualifications, powers and responsibilities]
ARTICLE IV: THE RIGHTS OF THE PEOPLE
Section 1: All persons born or naturalized in [Your Country’s Name] are citizens of [Your Country’s Name] and of the state wherein they reside. No state shall make or enforce any law which shall abridge the privileges or immunities of citizens.
Section 2: [Further details on the rights, freedoms, and responsibilities of the citizens, these could include things like freedom of speech, freedom of religion, right to a fair trial, etc.]
ARTICLE V: AMENDMENTS
Section 1: The [Legislative body] whenever two thirds of both Houses deem it necessary, shall propose Amendments to this Constitution, or, on the Application of the Legislatures of two thirds of the several states, shall call a Convention for proposing Amendments…
ARTICLE VI: GENERAL PROVISIONS
Section 1: [Any other items that need to be addressed, such as the official language, the national religion (or lack thereof), the national emblem, the process for international treaties, etc.]
ARTICLE VII: RATIFICATION
This Constitution shall be considered ratified when agreed upon by a majority of citizens through a free and fair vote.
Please remember that a constitution is a living document that will grow and change over time as your country evolves. This outline is just a starting point and may not include all the specific sections you need. For example, you might want to add sections addressing human rights, environmental protection, financial regulations, and so on.
This process should involve broad input from many different stakeholders, including legal experts, and should be reflective of the country’s culture, values, history, and aspirations for the future. Also, please note that the effective implementation of a constitution requires a strong rule of law and mechanisms for holding those in power accountable.
Because AI detectors suck and are the modern day equivalent of dowsing rods?
They’re circular. If the text is too predictable it was written by an LLM* but LLMs are designed to regurgitate the next word most commonly used by humans in any given context.
*AI is a complete misnomer for the hi-tech magic 8ball
The next most commonly used word would result in a loop of common word. LLMs do not work like that
In context. And that is exactly how they work. It’s just a statistical prediction model with billions of parameters.
This article was written to keep people as long on the page as possible. It didn’t get to the point before i left. Someone has a tl;dr?
Constitution is a text that appears many times on the internet. ChatGPT’s training set probably has multiple copies of it. So it’s likely ChatGPT will generate it. Therefore, the detectors are likely to flag it as AI-generated. That’s what I got from it, but I also found it difficult to parse. Maybe someone can correct me on this.
I thimk we need and AI to summarize the article. Edit: oh god, soon shit articles are gonna be optimized to not be AI summarizable