logoalt Hacker News

jonhohle • yesterday at 10:33 PM • 4 replies • view on HN

LLMs can’t count. Do you think they can balance parens?

Personally, I’ve wondered why they don’t just generate machine code.


Replies

shoobiedoo • yesterday at 11:13 PM

I never thought of that. Humans avoid machine code for many reasons. If LLM's don't need to produce human-readable output, then why not?

➕ show 1 reply
sharts • today at 7:39 AM

they can call tools to count tho?

rafram • today at 2:51 AM

I mean, is this an actual issue? There have to be plenty of developers using LLMs to write Lisp(s).

I have occasionally seen Claude models struggle to balance brackets/parens in nesting-heavy languages like Dart (Flutter), but it’s gotten much better.