Your question can be rephrased to “what would an actual difference look like.”
However, what you are asking underneath that, is a mix of “what is the difference” and “what is the PRACTICAL difference in terms of output”
Or in other words, if the output looks like what someone with understanding would say, how is it meaningfully different.
—-
Humans have a complex model of the world underlying their thinking. When I am explaining this to you, you are (hopefully) not just learning how to imitate my words. You are figuring out how to actually build a model of an LLM, that creates intuitions / predictions of its behavior.
In analogy terms, learning from this conversation, (understanding) is to create a bunch of LEGO blocks in your head, which you can then reuse and rebuild according to the rules of LEGO.
One of the intuitions is that humans can hallucinate, because they can have a version of reality in their head which they know is accurate and predicts physical reality, but they can be sick/ill and end up translating their sensory input as indicating a reality that doesn’t exist. OR they can lie.
Hallucinations are a good transition point to move back to LLMs, because LLMs cannot actually hallucinate, or lie. They are always “perceiving” their mathematical reality, and always faithfully producing outputs.
If we are to anthropomorphize it back to our starting point about “LLMs understand”, this means that even when LLMs “hallucinate” or “lie”, they are actually being faithful and honest, because they are not representing an alternate reality. They are actually precisely returning the values based on the previous values input into the system.
“LLMs understand” is misleading, and trojans in a concept of truth (therefore untruth) and other intuitions that are invalid.
—-
However, understanding this does not necessarily change how you use the LLMs 90% of the time, it just changes how you model them in your head, resulting in a higher match between observer reality and your predictive reality.
For an LLM this makes not difference, because its forecasting the next words the same way.
It depends on which human feedback was used to train the model. For humans, there are various communication models like the four-sides model. If the dataset has annotations for the specific facets of the communication model, then an LLM trained on this dataset will have specific probabilities that replicate that communication model. You may call this understanding what the prompter says, but it's just replication for me.
This isn’t a complete answer, but my short list for moving the tech many steps forward would be:
* replying with “I don’t know” a lot more often
* consistent responses based on the accessible corpus
* far fewer errors (hallucinations)
* being able to beat Pokémon reliably and in a decent time frame without any assistance or prior knowledge about the game or gaming in general (Gemini 2.5 Pro had too much help)
Your Question is an example of the difference.
Your question can be rephrased to “what would an actual difference look like.”
However, what you are asking underneath that, is a mix of “what is the difference” and “what is the PRACTICAL difference in terms of output”
Or in other words, if the output looks like what someone with understanding would say, how is it meaningfully different.
—-
Humans have a complex model of the world underlying their thinking. When I am explaining this to you, you are (hopefully) not just learning how to imitate my words. You are figuring out how to actually build a model of an LLM, that creates intuitions / predictions of its behavior.
In analogy terms, learning from this conversation, (understanding) is to create a bunch of LEGO blocks in your head, which you can then reuse and rebuild according to the rules of LEGO.
One of the intuitions is that humans can hallucinate, because they can have a version of reality in their head which they know is accurate and predicts physical reality, but they can be sick/ill and end up translating their sensory input as indicating a reality that doesn’t exist. OR they can lie.
Hallucinations are a good transition point to move back to LLMs, because LLMs cannot actually hallucinate, or lie. They are always “perceiving” their mathematical reality, and always faithfully producing outputs.
If we are to anthropomorphize it back to our starting point about “LLMs understand”, this means that even when LLMs “hallucinate” or “lie”, they are actually being faithful and honest, because they are not representing an alternate reality. They are actually precisely returning the values based on the previous values input into the system.
“LLMs understand” is misleading, and trojans in a concept of truth (therefore untruth) and other intuitions that are invalid.
—-
However, understanding this does not necessarily change how you use the LLMs 90% of the time, it just changes how you model them in your head, resulting in a higher match between observer reality and your predictive reality.
For an LLM this makes not difference, because its forecasting the next words the same way.
That's one of the best takes on this matter that I have seen in a long time.
(Ironically, I would not be too surprised if it was produced by an LLM.)
No LLM used for this. All errors and non errors are sadly my own.
It depends on which human feedback was used to train the model. For humans, there are various communication models like the four-sides model. If the dataset has annotations for the specific facets of the communication model, then an LLM trained on this dataset will have specific probabilities that replicate that communication model. You may call this understanding what the prompter says, but it's just replication for me.
This isn’t a complete answer, but my short list for moving the tech many steps forward would be:
* replying with “I don’t know” a lot more often
* consistent responses based on the accessible corpus
* far fewer errors (hallucinations)
* being able to beat Pokémon reliably and in a decent time frame without any assistance or prior knowledge about the game or gaming in general (Gemini 2.5 Pro had too much help)
The difference comes when it receives novel input
What is novel input?
Something it hasn't seen in it's training before.
Such as, trying to get an AI to create a design mockup of mastodon but it keeps falling over at laying out the page correctly: https://social.coop/@scottjenson/114593227688326501