Hacker News Reader

Comment by zarzavat | Hacker News Reader

Humans are also vulnerable to the reversal curse! When you learn languages you have to learn both directions (chat is cat and cat is chat), anybody who has built an anki deck will know this, otherwise you will be better in one direction than the other.

View on HN

Not just languages. It's the case with everything. Easy to spot when you're tutoring someone. You can see they learned "force is mass times acceleration" or "for( ... ) is how you make the same code run multiple times" - they can tell you that when quizzed! But you know they haven't comprehended it until they can reverse it - "I need to compute the mass of the object, which I see accelerating this much under this force; I can pull that from F=ma -> m=F/a!", or "I want to run this code several times, I need a `for` loop!". And getting to that stage is often the longest and most difficult part.

Interesting; your message hints at a sharp gap between using language stochastically (eg being able to repeat what you've heard) vs using language to express deeper knowledge/understanding.

A common argument is that LLM by their nature only model the former, not the latter.

My point is that LLMs can do both, the same way humans can. We don't learn or recall reversals automatically either - we memorize them separately, or run an inference step (which, done often enough, leads to memorization). Reversals aren't free - not for LLMs, and not for our own minds.

Yes the difference is that LLMs learn statically: they train and that’s it. Humans dynamically: they revisit learned facts and synthesize new ones. If you force an LLM-like training process in a human, by doing rote memorization without any exercises, then you get LLM-like results in that human.

This suggests that you may need to train an LLM on its own output. Goes against the conventional wisdom!

I think this “wisdom” is not really agreed upon, and in fact I’ve seen a few works successfully leverage synthetic data (including a cool one from Sergey Levine et al recently).

As one gets deeper into learning another language, it’s also important to be aware that the meanings of words in different languages rarely map to each other in clean bijections. Common words especially tend to be semantic clouds, not fixed points of meaning.

I don’t know French, but I am sure there are many cases where an English phrase or sentence that includes ‘cat’ should not be translated into French with ‘chat’ and vice versa. (When asked, GPT-4 offers two such examples: "let the cat out of the bag” and "avoir un chat dans la gorge.")

I don’t mean to suggest, though, that memorizing word pairs is not a good way to learn vocabulary in another language. For me, it was an essential step in acquiring the second language that I am now fluent in (Japanese).

I think this has as much to do with abstract vs. concrete words as common vs. uncommon. If you had to pick a word corresponding to “chat” it’s quite clearly “cat”, despite a few different expressions. But it’s rather difficult to translate “justement” to English, or “random” to French, without further context.

Words are always semantic clouds. Not getting that is what sent philosophy down many a dead end, and the source of plenty of arguments regular people get into all the time. One doesn't need to try mapping between two languages - it's enough problem trying to map within the language itself.

Reply on news.ycombinator.com