AI researchers revisit Minqi Jiang 2022 exploration paper
Minqi Jiang's 2022 paper General Intelligence Requires Rethinking Exploration is drawing renewed attention from AI researchers. Submitted to arXiv on November 15 under identifier 2211.07819, the work argues that general intelligence requires new exploration approaches beyond existing reinforcement learning. Will Brown, research lead at Prime Intellect, and Edward Grefenstette, following his departure from Meta, highlighted the paper's forward-looking ideas on self-teaching systems.
#87Edward Grefenstette@EGREFENNice of @jennyzhangzt to share this paper, which I selfishly think was ahead of its time. The context was that I was leaving Meta to do another startup, and thought I would not be writing papers for years. Of course, @MinqiJiang had all the good ideas + did most of the writing 😅
@MinqiJiang @willccbb And rethink it.
Minqi Jiang@MinqiJiang@willccbb it's time to explore
#339will brown@WILLCCBBwas reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching
then i realized it was from 2022
will brown@willccbbwas reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching then i realized it was from 2022
#957Andrew Drozdov@MRDROZDOVmany such cases
will brown@willccbbwas reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching then i realized it was from 2022
@willccbb it's time to explore
will brown@willccbbwas reading a paper last night that felt very timely and refreshing, like the sort of thing that was bound to anchor the next wave of innovation in self-teaching then i realized it was from 2022
@egrefen @jennyzhangzt Thanks for the kind words (and for originally instigating this paper)!
Talking through and rethinking these ideas together over the ~6 months spent writing this was the most transformative part of my PhD, when I figured out to a great extent what I believed as a researcher.
Edward Grefenstette@egrefenNice of @jennyzhangzt to share this paper, which I selfishly think was ahead of its time. The context was that I was leaving Meta to do another startup, and thought I would not be writing papers for years. Of course, @MinqiJiang had all the good ideas + did most of the writing 😅