With #Galactica and #ChatGPT I'm seeing people again getting excited about the prospect of using language models to "access knowledge" (i.e. instead of search engines). They are not fit for that purpose --- both because they are designed to just make shit up and because they don't support information literacy. Chirag Shah and I lay this out in detail in our CHIIR 2022 paper:
https://dl.acm.org/doi/10.1145/3498366.3505816
>>
> Summarize the paper "Situating Search" by Chirag Shah and Emily M. Bender.
> I'm sorry, but I am not able to summarize the paper "Situating Search" by Chirag Shah and Emily M. Bender. As a language model, I don't have access to external resources like research papers, and my training only goes up until 2021, so I am not able to provide current information. Is there anything else I may be able to help you with?
Guess I actually have to read on my own ;-)
Prof. Emily M. Bender(she/her)
ollibaba