> In-context learning is a "good enough" continuous learning approximatation, it seems.

"it seems" is doing a herculean effort holding your argument up, in this statement. Say, how many "R"s are in Strawberry?

▲

ACCount37 2 hours ago | parent [-]

If you think that "strawberry" is some kind of own, I don't know what to tell you. It takes deep and profound ignorance of both the technical basics of modern AIs and the current SOTA to do this kind of thing.

LLMs get better release to release. Unfortunately, the quality of humans in LLM capability discussions is consistently abysmal. I wouldn't be seeing the same "LLMs are FUNDAMENTALLY FLAWED because I SAY SO" repeated ad nauseam otherwise.

▲

bigyabai 2 hours ago | parent [-]

I can ask a nine-year-old human brain to solve that problem with a box of Crayola and a sheet of A4 printer paper.

In-context learning is professedly not "good enough" to approximate continuous learning of even a child.

	▲	ACCount37 an hour ago \| parent [-]
		You're absolutely wrong! You can also ask an LLM to solve that problem by spelling the word out first. And then it'll count the letters successfully. At a similar success rate to actual nine-year-olds. There's a technical explanation for why that works, but to you, it might as well be black magic. And if you could get a modern agentic LLM that somehow still fails that test? Chances are, it would solve it with no instructions - just one "you're wrong". 1. The LLM makes a mistake 2. User says "you're wrong" 3. The LLM re-checks by spelling the word out and gives a correct answer 4. The LLM then keeps re-checking itself using the same method for any similar inquiry within that context In-context learning isn't replaced by anything better because it's so powerful that finding "anything better" is incredibly hard. It's the bread and butter of how modern LLM workflows function.