Just stumbled across “Are Emergent Abilities of Large Language Models a Mirage?” paper and it is quite interesting. Can’t believe I just came across this today. At a time, when everyone is quick to note “emergent capabilities” in LLMs, it is great to have another perspective (s).
Just stumbled across “Are Emergent Abilities of Large Language Models a Mirage?” paper and it is quite interesting. Can’t believe I just came across this today. At a time, when everyone is quick to note “emergent capabilities” in LLMs, it is great to have another perspective (s).
Easily my favourite paper since “Exploiting Novel GPT-4 APIs”!!!