[Nevermark]

Humans learn vast amounts of information from examples.

They learn their first words, how to walk, what a cat looks like from many perspectives, how to parse a visual scene, how to parse the spoken word, interpret facial expressions and body language, how different objects move, how different creatures behave, different materials feel, what things cause pain, what things taste like and how they make them feel, how to get what they want, how to climb, how not to fall, all by trial & example. On and on.

And yes, as we get older we get better and better at learning 2nd hand from others verbally, and when people have the time to show us something, or with tools other people already invented.

Like how a post-trained model picks up on something when we explain it via a prompt.

But that is not the kind of training being done by models at this stage. And yet they are learning concepts (pre-prompt) that, as you point out, you & I had to have explained to us.

[Jensson]

> Like how a model picks up on when we explain something to it after it has been trained.

Models don't learn by you telling them something, the model doesn't update itself. A human updates their model when you explain how something works to them, that is the main way we teach humans. Models don't update themselves when we explain how something works to them, that isn't how we train these models, so the model isn't learning its just evaluating. It would be great if we could train models that way, but we can't.

> Humans learn vast amounts of information from examples.

Yes, but to understand things in school those examples comes with an explanation of what happens. That explanation is critical.

For example, a human can learn to perform legal chess moves in minutes. You tell them the rules each piece has to follow and then they will make legal moves in almost every case. You don't do it by showing them millions of chess boards and moves, all you have to do is explain the rules and the human then knows how to play chess. We can't teach AI models that way, this makes human learning and machine learning fundamentally different still.

And you can see how teaching rules creates a more robust understanding than just showing millions of examples.

[Nevermark]

> you explain how something works to them, that is the main way we teach humans

I am curious who taught you to recognize sounds, before you understood language, or how to interpret visual phenomena, before you were capable of following someone’s directions.

Or recognize words independent of accent, speed, pitch, or cadence. Or even what a word was.

Humans start out learning to interpret vast amounts of sensory information, and predictions of results of there physical motor movements, from a constant stream of examples.

Over time they learn the ability to absorb information indirectly from others too.

This is no different from models, except that it turns out, they can learn more things, at a higher degree of abstraction, just from example than us.

And work on their indirect learning (I.e. long term retention of information we give them via prompts), is just beginning.

But even as adults, our primary learning mode is experience is from the example situations we encounter non-stop as we navigate life.

Even when people explain things, we generalize a great deal of nuance and related implications beyond what is said.

“Show, don’t tell”, isn’t common advice for no reason. We were born example generalizers.

Then we learn to incorporate indirect information.

[Jensson]

You are right, but I think it is really important to have this difference in learning in mind, because not being able to learn rules during training is the main weakness in these models currently. Understanding that weakness and how that makes their reasoning different from humans is key both to using these models and for any work on improving them.

For example, you shouldn't expect it to be able to make valid chess moves reliably, that requires reading and understanding rules which it can't do during training. It can get some understanding during evaluation, but we really want to be able to encode that understanding into the model itself rather than have to keep it in eval time.

[Nevermark]

Yes, agreed, you are right too.

There is a distinction between reasoning skills learned inductively (generalizing from examples), and reasoning learned deductively (via compact symbols or other structures).

The former is better at recognition of complex patterns, but can incorporate some basic deduction steps.

But explicit deduction, once it has been learned, is a far more efficient method of reasoning, and opens up our minds to vast quantities of indirect information we would never have the time or resources to experience directly.

Given how well models can do at the former, it’s going to be extremely interesting to see how quickly they exceed us at the latter - as algorithms for longer chains of processing, internal “whiteboarding” as a working memory tool for consistent reasoning over many steps and many facts, and long term retention of prompt dialogs, get developed!