Large language models' surprise emergent behavior written off as 'a mirage'

Forget those huge hyped-up systems, that smaller one might be right for you. And here's why

Analysis  GPT-3, PaLM, LaMDA and other next-gen language models have been known to exhibit unexpected "emergent" abilities as they increase in size. However, some Stanford scholars argue that's a consequence of mismeasurement rather than miraculous competence.…

analysis behavior gen gpt gpt-3 lamda language language models large language models next next-gen palm scholars stanford surprise systems