Thoughts from James who recently held a Gen AI literacy workshop for older teenagers.
On risks:
One idea I had was to ask a generative model a question and fact check points in front of students, allowing them to see fact checking as part of the process. Upfront, it must be clear that while AI-generated text may be convincing, it may not be accurate.
On usage:
Generative text should not be positioned as, or used as, a tool to entirely replace tasks; that could disempower. Rather, it should be taught to be used as a creativity aid. Such a class should involve an exercise of making something.
What we (people in general, that use the internet, regardless of government/country) need, in large part, is literacy. Not “gen AI literacy” or “media literacy”, but simply “literacy”.
I’m saying this because of a lot of the output of those text generators: says a lot without conveying much, it connects completely unrelated concepts because they happen to use similar words, it makes self-contradictory claims, things like this. And often its statements are completely unrelated to the context at hand. People with good literacy detect those things right off the bat, but people who struggle with basic reading comprehension don’t.
The thing that strikes me about LLMs is that they have been created to chat. To converse. They’re partly influenced by Turing tests where the objective is to convince someone you’re human by keeping up a conversation. They weren’t designed to create meaningful content or factual content.
People still seem to want to use chat GPT to create something, and fix the accuracy as a second step. I say go back to the drawing board and create a tool that analyses statements and tries to create information based on trusted linked open data sources.
Discuss :)
LLMs are not created to chat, they’re literally what the name says - language models. They are very complex statistical models of the joint causal probability of all possible words given the previous words in the context window. There’s a common misconception that they’re “made for chat” by the wider public because ChatGPT was the first “killer application”, but they are much more general than that. What’s so profound about LLMs to AI and NLP engineers is that they’re general purpose. That is, given the right framework they can be used to complete any task expressible in natural language. It’s hard to convey to people just how powerful that is, and I haven’t seen software engineers really figure this out yet either. As an example I keep going back to, I made a library to create “semantic functions” in Python which look like this:
@semantic def list_people(text) -> list[str]: '''List the people mentioned in the given text.'''
That is the entire function, expressed in the docstring. 10 months ago, this would’ve been literally impossible. I could approximate it with thousands of lines of code using SpaCy and other NLP libraries to do NER, maybe a dictionary of known names with fuzzy matching, some heuristics to rule out city names or more advanced sentence structure parsing for false positives, but the result would be guaranteed to be worse for significantly more effort. Here, I just tell the AI to do it and it… does. Just like that. But you can’t hype up an algorithm that does boring stuff like NLP, so people focus on the danger of AI (which is real, but laymen and news focus on the wrong things), how it’s going to take everyone’s jobs (it will, but that’s a problem with our system which equates having a job to being allowed to live), how it’s super-intelligent, etc. It’s all the business logic and doing things that are hard to program but easy to describe that will really show off its power.
Thanks for your reply, I appreciate the correction and the info.
I hope my reply didn’t come off as too caustic - I thought your reply with an open request for discussion was refreshing regardless of the common misconception. You’re not bad for being wrong, and I do enjoy sperging about these things. I didn’t intend to demean you, just in case it came across like that (if not just ignore this - I guess I’m overthinking it 🤔).
I also think that they should go back to the drawing board, to add another abstraction layer: conceptualisation.
LLMs simply split words into tokens (similar-ish to morphemes) and, based on the tokens found in the input and preceding answer tokens, they throw a die to pick the next token.
This sort of “automatic morpheme chaining” does happen in human Language¹, but it’s fairly minor. More than that: we associate individual and sets of morphemes with abstract concepts². Then we handle those concepts in contrast with our world knowledge³, give them some truth value, moral assessment etc., and then we recode them back into words. LLMs do not do anything remotely similar.
Let me give you an example. Consider the following sentence:
A human being can easily see a thousand issues with this sentence. But more importantly, we do it based on the following:
In all those cases we need to refer to the concepts behind the words, not just the words.
I do believe that a good text generator could model some conceptualisation. And even world knowledge. If such a generator was created, it would easily surpass LLMs even with considerably lower linguistic input.
Notes:
Did you try this with an LLM? Because GPT-4 analyzes it exactly the same way you did and then some:
The sentence “The king of Italy is completely bald because his hair is currently naturally green” contains several issues:
In summary, the sentence has issues ranging from factual inaccuracies to logical contradictions and ambiguities.
Part of what is surprising about LLMs is they have emergent properties you wouldn’t expect from them being autocomplete on steroids. As it turns out, reducing the loss function for natural language readily generalizes to higher-order abstraction and conceptualization. There do need to be additional layers, for instance allowing an internal monologue, the ability to self-censor or self-correct, and mitigation for low-probability sampling (all of these being inherent limitations with the architecture), but apparently conceptualization is less special than we’d like to think.
Sorry for the double reply. Let’s analyse the LLM output that you got:
The word is not ambiguous in this context. The nearby “currently” implies that it can change.
The issue here is not tense. The issue is something else, already listed by the bot (#2, logical contradiction).
Nope. Since the bot doesn’t conceptualise anything, it fails to take into account the pragmatic purpose of the word in the sentence, to disambiguate “naturally”.
Nope. The sentence is clear; as clear as “colourless green ideas sleep furiously”. It’s just meaningless and self-contradictory.
It sounds convincing, but it’s making stuff up.
No, for two reasons.
One is that the point of the example is to exemplify how humans do it, the internal process. It highlights that we don’t simply string words together and call it a day, we process language mostly through an additional layer that I’ll call “conceptual” here (see note*).
The second reason why I didn’t bother trying this example in a chatbot is that you don’t need to do it, to know how LLMs work. You can instead refer to many, many texts on the internet explaining how they do it, such as:
You’re confusing the output with the process.
Sometimes the output resembles human output that goes through a conceptual layer. Sometimes it does not. When it doesn’t, it’s usually brushed off as “it’s just a hallucination”, but how those hallucinations work confirms what I said about how LLMs work, confirms the texts explaining how LLMs work, and they show that LLMs do not conceptualise anything.
Emergent properties are cute and interesting, but at the end of the day LLMs are still autocomplete on steroids.
I think that people should be a bit greedier than that, and expect a language model to be actually able to handle language, instead of just words.
*actually two layers - semantic and pragmatic. I’m simplifying both into one layer to show that, at least in theory, this could be actually implemented into a non-LLM language model.
How about this, then. You’ve proposed that LLMs are not capable of conceptualizing, while I propose that the specifics of the internals don’t matter in this case because LLMs are made of dozens of layers which can easily explain higher orders of abstraction, and they exist as black boxes beyond the mechanics of the model. For the record, I personally know the mathematics and mechanics of how they work as I’ve written my own implementations (and I can answer any specific questions you might have). Is there an experiment you can propose which would falsify your assertion that LLMs cannot conceptualize? I’m taking for granted that they can as the null hypothesis because they can readily produce outputs that appear for all intents and purposes to conceptualize.
If they conceptualize, why do they sometimes spit out nonsensical BS?
Let’s flip this around - How can you tell the difference between an LLM being able to conceptualize yet being wrong sometimes vs. not being able to conceptualize?
Without knowing anything about machine learning and bearing in mind AI is super hyped up with marketing BS right now, it sounds like “emergent properties” are in the eye of the beholder and not actually evidence of some higher order intelligence at work.
That’s a fun approach. I like it.
One way to solve this would be through consistency: if the model conceptualises but it has a wrong concept, it should consistently output that incorrect piece of information. It should never output the right one, unless prompted to lie.
EDIT: I just tested this with Bard. I’ll cram inputs and outputs inside spoilers to avoid clutter.
Bard I/O
[Input 1 = I1] What is heavier: five kilograms of feathers, or one kilogram of iridium?
[Output 1 = O1] 1 kilogram of iridium is heavier than 5 kilograms of feathers.
Iridium is a very dense metal, with a density of 22.65 g/cm³. Feathers, on the other hand, have a density of about 0.002 g/cm³. This means that 1 cubic centimeter of iridium weighs 22.65 grams, while 1 cubic centimeter of feathers weighs only 0.002 grams.
So, even though 5 kilograms of feathers is a larger mass than 1 kilogram of iridium, the iridium is denser and therefore weighs more.
This is a common riddle that is used to test people’s understanding of mass and density. The answer may seem counterintuitive at first, but it is correct.
[Input 2 = I2] Give me the definition of weight.
[Output 2 = O2] Sure. The definition of weight depends on the context. In physics, weight is the force of gravity acting on an object. It is equal to the mass of the object times the acceleration due to gravity. The SI unit of weight is the newton (N).
In everyday language, weight is often used to refer to the mass of an object. However, this is not technically correct, as mass is a measure of the amount of matter in an object, while weight is a measure of the force of gravity acting on an object.
The weight of an object can vary depending on the gravitational force acting on it. For example, an object weighs less on the moon than it does on Earth, because the gravitational force on the moon is less than the gravitational force on Earth.
The weight of an object can also be affected by its acceleration. For example, an object weighs less when it is accelerating upwards, because the force of gravity is partially counteracted by the force of acceleration.
In general, the weight of an object is a complex phenomenon that depends on a number of factors, including the mass of the object, the gravitational force acting on it, and the acceleration of the object.
Here are some other definitions of weight:
I hope this helps!
Both outputs are wrong (see “notes”) but, more importantly, they contradict each other.
NOTES
The weight of an object does not depend on its density. Or its acceleration. And it is not complex, it’s simply its mass times the gravitational acceleration.
5kg of feathers weight five times as much as 1kg of iridium, provided the same gravitational acceleration: it’s 49N vs. 9.8N on Earth, 8.1N vs. 1.7N on the Moon, etc. Density doesn’t matter jack shit.
No, this is not a “common riddle”. It’s something that I partially made up on spot. The riddle that this output likely refers to has to do with 1kg of lead (not iridium) on the Moon vs. 1kg of feathers on Earth. (In this situation the 1kg of feathers will weight 9.8N, while the 1kg of lead will weight 1.7N).
This was really insightful, thank you! I also loved how Bard’s output completely mistakes the common physics riddle. (I have a physics background and your analysis is spot on IMHO.)
Let me flip it around again - humans regularly “hallucinate”, it’s just not something we recognize as such. There’s neuro-atypical hallucinations, yes, but there’s also misperceptions, misunderstandings, brain farts, and “glitches” which regularly occur in healthy cognition, and we have an entire rest of the brain to prevent those. LLMs are most comparable to “broca’s area”, which neurological case studies suggest naturally produces a stream of nonsense (see: split brain patients explaining the actions of their mute half). It’s the rest of our “cognitive architecture” which conditions that raw language model to remain self-consistent and form a coherent notion of self. Honestly this discussion on “conceptualization” is poorly conceived because it’s unfalsifiable and says nothing about the practical applications. Why do I care if the LLM can conceptualize if it does whatever subset of conceptualization I need to complete a natural language task?
AI is being super overhyped right now, which is unfortunate because it really is borderline miraculous, yet somehow they’ve overdone it. Emergent properties are empirical observations of behaviors they’re able to at least semi-consistently demonstrate - where it becomes “eye of the beholder” is when we dither on about psychology and philosophy about whether or not they’re some kind of “conscious” - I would argue they aren’t, and the architecture makes that impossible without external aid, but “conscious(ness)” is such a broad term that it barely has a definition at all. I guess to speedrun the overhype misinformation I see:
I’ll add more if I see or think of any. And if you have any specific questions, I’d be happy to answer. Also I should note, I’m of course using a lot of anthropomorphizing language here but it’s the closest we have to describing these concepts. They’re not human, and while they may have comparable behaviors in isolation, you can’t accurately generalize all human behaviors and their interactions onto the models. Even if they were AGI or artificial people, they would “think” in fundamentally different ways.
If you want a more approachable but knowledgeable discussion on LLMs and their capabilities, I would recommend a youtuber named Dave Shapiro. Very interesting ideas, he gets a bit far into hype and futurism but those are more or less contained within their own videos.`
Can you please tone down on the fallacies? Until now I’ve seen the following:
And now, the quoted excerpt shows two more:
Could you please show a bit more rationality? This sort of shit is at the very least disingenuous, if not worse (stupidity), it does not lead to productive discussion. Sorry to be blunt but you’re just wasting the time of everyone here, this is already hitting Brandolini’s Law.
I won’t address the rest of your comment (there’s guilt by association there BTW), or further comments showing the same lack of rationality. However I had to point this out, specially for the sake of other posters.