Early this year, there was some buzz about a new site called tl;dr papers, which claimed to "use machine learning to summarize arguments in scientific papers so that even a seven-year-old could understand them". From the moment I tried to visit the site it was down, so I put a watch on it, hoping to be able to do some fun learning when it came back up. But it never did. Earlier this week I got an alert that content at https://www.tldrpapers.com/ had changed, but it just redirects now to https://elicit.org/, which has been around a little longer, according to Archive.org, so tl;dr didn't become Elicit...
Now that I scroll to the bottom of the Verge article, I see I could've saved myself some hope (or maybe I saw that before and just didn't want to believe):
Unfortunately, although tl;dr papers has had a rapturous reception among the academic world, its time in the spotlight looks limited. After going viral this weekend, the website has been labeled “under maintenance,” and the site’s creators say they have no plans to maintain it in the future. (They also mention that other tools have been built that perform the same task.)
Anyhoo, I guess I'm now off to play with Elicit, which may be similar to these other Research Network and Discovery Tools I've been meaning to explore. Or maybe it's something completely different.
So what is Elicit?
Elicit is a research assistant using language models like GPT-3 to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table.