RT by @awnihannun: There was a nice time where researchers talked about various ideas quite openly on twitter. (before they disappeared into the gold mines :)). (opens in new tab)

<p>There was a nice time where researchers talked about various ideas quite openly on twitter. (before they disappeared into the gold mines :)).<br> <br> My guess is that you can get quite far even in the current paradigm by introducing a number of memory ops as "tools" and throwing them into the mix in RL. E.g. current compaction and memory implementations are crappy, first, early examples that were somewhat bolted on, but both can be fairly easily generalized and made part of the optimizati...