Icestorm over Boston Sunday night -- I hope I don't get stuck in San Francisco!
But: If I do, what should I do?
Icestorm over Boston Sunday night -- I hope I don't get stuck in San Francisco!
But: If I do, what should I do?
Is it a good omen when your dental crown comes off in the middle of a paper submission?
The problem of BlueSky: now since we all followed one another, we have nothing else to say.
"Look at this for 10 minutes, then go an rewrite your peer-review"
Thanks, Leo!
Publishing is cruel, because we are reviewing our peers AND are destined to disagree.
Also, so far I have not seen any shred of work on how to evaluate the topical coherence of a response.
(I am not referring to a linguistic "fluency", but whether the response makes sense)
I also still think we don't have good metrics for evaluating RAG.
Neither one-big-relevance-prompt-grading (like UMBRELLA), nor breaking it into finer nuggets/grading rubrics are a done deal. We are still figuring out too many pieces.
My bet is that in the coming weeks, you will see people who are based in the US acting strangely.
You may find people who are working for US tech giants to advocate for an "America First" stance. You may find people working for US academic institutions to not comment publicly.