Post

ALMOST EVERY PEER REVIEWED PAPER HAS A SUMMARY OF KEY POINTS RIGHT BELOW ITS TITLE

One thing you give to potential editors in hiring tests is a badly written paper whose abstract is barely comprehensible and omits key info. Generally you don’t have to look far to find one… 1/2

I’m hardly an AI lobbyist but we have to be honest LLMs will write summaries better than many authors, especially for lay readers. Feels like one thing they’re inarguably good at (though not perfect given hallucinations etc).

So (A) even if I agree that LLM summarization is sufficiently more reliable than all authors everywhere, just generate the summary and drop it in front of the paper, don’t waste the compute and my time with a chatbot; and

(B) if you have to caveat about hallucinations you’re right back where you started with the problem of unreliable abstracts

Ideally - but what do you do when there are so many potentially relevant papers you could not possibly read them all? It’s clear to me lots of people want to find reasons not to read many of them and much of what is written in the ones they do..

Not clear if you mean a researcher could not read all the papers OR could not read all the abstracts.