alt Hacker NewsI 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.
Replies
8note • yesterday at 11:36 PM
why is the breakdown from words to letters your highest priority thing to add to the training data?
what problem does this allow you to solve that you couldnt otherwise?
➕ show 1 reply
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.