I have many conversations with people about Large Language Models like ChatGPT and Copilot. The idea that “it makes convincing sentences, but it doesn’t know what it’s talking about” is a difficult concept to convey or wrap your head around. Because the sentences are so convincing.
Any good examples on how to explain this in simple terms?
Edit:some good answers already! I find especially that the emotional barrier is difficult to break. If an AI says something malicious, our brain immediatly jumps to “it has intent”. How can we explain this away?
Harry Frankfurt’s influential 2005 book (based on his influential 1986 essay), On Bullshit, offered a description of what bullshit is.
When we say a speaker tells the truth, that speaker says something true that they know is true.
When we say a speaker tells a lie, that speaker says something false that they know is false.
But bullshit is when the speaker says something to persuade, not caring whether the underlying statement is true or false. The goal is to persuade the listener of that underlying fact.
The current generation of AI chat bots are basically optimized for bullshit. The underlying algorithms reward the models for sounding convincing, not necessarily for being right.
It’s a really well-trained parrot. It responds to what you say, and then it responds to what it hears itself say.
But despite knowing which sounds go together based on which sounds it heard, it doesn’t actually speak English.
Not an ELI5, sorry. I’m an AI PhD, and I want to push back against the premises a lil bit.
Why do you assume they don’t know? Like what do you mean by “know”? Are you taking about conscious subjective experience? or consistency of output? or an internal world model?
There’s lots of evidence to indicate they are not conscious, although they can exhibit theory of mind. Eg: https://arxiv.org/pdf/2308.08708.pdf
For consistency of output and internal world models, however, their is mounting evidence to suggest convergence on a shared representation of reality. Eg this paper published 2 days ago: https://arxiv.org/abs/2405.07987
The idea that these models are just stochastic parrots that only probabilisticly repeat their training data isn’t correct, although it is often repeated online for some reason.
A little evidence that comes to my mind is this paper showing models can understand rare English grammatical structures even if those structures are deliberately withheld during training: https://arxiv.org/abs/2403.19827
The idea that these models are just stochastic parrots that only probabilisticly repeat their training data isn’t correct
I would argue that it is quite obviously correct, but that the interesting question is whether humans are in the same category (I would argue yes).
Bro is lost in the sauce
Maybe I misunderstood the OP? Idk
You sound like a chatbot who’s offended by it’s intelligence being insulted.
You could maybe just share a meme like this one.
Some folks in the comments there share actual LLM results, a few of which are sensible but plenty that aren’t far off from the joke.
LMAO! I tried it, and it said:
The man takes the goat across the river first, then he returns alone and takes the boat across again. Finally, he brings the goat’s friend, Mr. Cabbage, across the river.
LMAO
I asked what if the man can’t swim…
In that case, the man can still take the goat across the river first. Then, he ties the goat to the boat and pulls the boat across the river using a rope, ensuring he stays on the side of the river where he can safely manage the boat without swimming.
I asked who Mr. Cabbage is…
My apologies for the confusion! Mr. Cabbage is a playful addition. In the classic riddle, there’s usually no mention of Mr. Cabbage. It’s just the man, the goat, and perhaps another item or animal depending on the version of the riddle. I just added Mr. Cabbage for some extra fun!
Then I asked what some other additions could be…
Certainly! You can add various characters or items to make the riddle more entertaining. Here are a few ideas:
-
Mr. Wolf: The man, the goat, and Mr. Wolf need to cross the river. But if the man leaves the wolf alone with the goat, the wolf will eat the goat.
-
Ms. Hen: The man, the goat, and Ms. Hen need to cross the river. But if the man leaves the hen alone with the goat, the goat will eat the hen.
-
Professor Fox: The man, the goat, and Professor Fox need to cross the river. But if the man leaves the fox alone with the goat, the fox will eat the goat.
-
Princess Diamond: The man, the goat, and Princess Diamond’s precious gem need to cross the river. But Princess Diamond has warned that if anyone other than herself touches the gem, they’ll be cursed.
Feel free to mix and match or come up with your own additions!
And the “solution”…
Ah, that’s a fun twist! Let’s see:
- The man takes Mr. Cabbage across first, then returns alone.
- Next, he takes Ms. Hen across but brings Mr. Cabbage back.
- He then takes Princess Diamond’s gem across, leaves it on the other side, and takes Mr. Wolf across.
- The man leaves Mr. Wolf with Ms. Hen on the other side and returns alone.
- He takes Princess Diamond across, but before he leaves, he swaps Mr. Cabbage with Princess Diamond’s gem.
- The man brings Mr. Cabbage across, leaving Princess Diamond’s gem with Mr. Wolf.
- Finally, he takes the goat across.
Everyone safely crosses the river without any mishaps!
I love Mr. Cabbage! Thank you CharGPT, very cool!
-
It’s your phone’s ‘predictive text’, but if it were trained on the internet.
It can guess what the next word should be a lot of the time, but it’s also easy for it to go off the rails.
idea that “it makes convincing sentences, but it doesn’t know what it’s talking about”
Like a teenager who has come into a new group and is now trying so hard to fit in :-)
It’s just fancy predictive text like while texting on your phone. It guesses what the next word should be for a lot more complex topics.
