alt Hacker NewsWildly speculating here, but if you buy that human brains have innate / evolved syntactic knowledge, and that this knowledge projects itself as the common syntactic forms across the bulk of human languages, then it’s no surprise that LLMs don’t have particularly deep grooves for s-expressions, regardless of the programming language distribution of the training set.
Replies
js8 • today at 5:35 AM
There is an interesting on-going research https://dnhkng.github.io/posts/sapir-whorf/ that shows LLMs think in a language-agnostic way. (It will probably get posted to HN after it is finished.)
lgessler • today at 4:24 AM
Is Java or Haskell any closer to human language?
OK, I'll bite. I want to know more of the reasoning behind this, because I think it implies that S-expressions are alien to the innate/evolved syntactic knowledge in human languages. A lot of American linguistics, like Chomsky's gropings for how to construct universal grammar and deep syntax trees, or the lambda calculus of semantic functions, looks like S-expressions, and I think that's because there was some coordination between human linguists and computer science (Chomsky was, after all, at MIT). At the same time, I've had a gut instinct that these theories described some languages (like English) better than others (like ancient Greek), requiring more explanation of changes between deep structure and surface structure for languages that were less like English. If models trained on actual language handle s-expressions poorly, that could imply that s-expressions were not a good model for the deep structure of human language, or that the deep-structure vs surface-structure model did not really work. I'd be very happy to learn more about this.