LLMs are bad at creating abstraction boundaries since inception. People have been calling it out since inception. (Heck, even I got a twitter post somewhere >12 months old calling that out, and I'm not exactly a leading light of the effort)

It is in no way size-related. The technology cannot create new concepts/abstractions, and so fails at abstraction. Reliably.

▲

TeMPOraL an hour ago | parent | next [-]

> The technology cannot create new concepts/abstractions, and so fails at abstraction. Reliably.

That statement is way too strong, as it implies either that humans cannot create new concepts/abstractions, or that magic exists.

	▲	atty 37 minutes ago \| parent \| next [-]
		I think both your statement and their statement are too strong. There is no reason to think LLMs can do everything a human can do, which seems to be your implication. On the other hand, the technology is still improving, so maybe it’ll get there.
	▲	reactordev 34 minutes ago \| parent \| prev [-]
		That’s a straw man argument if I’ve ever seen one. He was talking about technology. Not humans.

▲

w0m 2 hours ago | parent | prev [-]

I believe his argument is that now that you've defined the limitation, it's a ceiling that will likely be cracked in the relatively near future.

▲

emp17344 2 hours ago | parent [-]

Well, hallucinations have been identified as an issue since the inception of LLMs, so this doesn’t appear true.

▲

w0m a minute ago | parent | next [-]

I mean, Hallucinations are 95% better now than the first time I heard the term and experienced them in this context. To claim otherwise is simply shifting goalposts. No one is saying it's perfect or will be perfect, just that there has been steady progression and likely will continue to be for the foreseeable future.

▲

johnfn 35 minutes ago | parent | prev [-]

Hallucinations are more or less a solved problem for me ever since I made a simple harness to have Codex/Claude check its work by using static typechecking.

	▲	emp17344 26 minutes ago \| parent [-]
		But there aren’t very many domains where this type of verification is even possible.