In context learning is hands down the biggest breakthrough of LLMs. The flexibility the model displays without updating weights is genuinely mind blowing, bordering on absurd especially if you've trained other kinds of models before.
GPT 3.5's (4 is much much better) addition accuracy tanks after 2 digits. However, by approaching arithmetic as an algorithm to be performed and taught similarly to how it's done with people, you can supercharge accuracy to basically 100% for up to 13 digit addition and >90% after.
See here - https://imgur.com/a/w3DAYOi from the paper - https://arxiv.org/abs/2211.09066
GPT 3.5's (4 is much much better) addition accuracy tanks after 2 digits. However, by approaching arithmetic as an algorithm to be performed and taught similarly to how it's done with people, you can supercharge accuracy to basically 100% for up to 13 digit addition and >90% after.