Find research that..
has nothing to do with what you’re working on, but is interesting
looks like what you’re interested in, but is different in content
is similar to what you’re interested in, but is very different
is in a very different discipline or medium, but has a similar idea to... See more
after studying in basically every library / study spot in cambridge, I've found that the best study spots are still mom & pop cafes where there is a sense of *life* vs. institutional heaviness. In these life-filled places, I've found that insights come through more easily, esp when I "borrow" from the auric field of PhD students doing psets and... See more
The performance of highly advanced artificial intelligence models is constrained by the knowledge available to them.
Even if GPT-6 is smarter than you, if it doesn’t have access to the right information, it won’t be able to say anything truly interesting.
Every now and again, a few of these fragments will stick to each other and nucleate , crystallizing a substantial, synthetic analysis out of all of those bits and pieces I’ve salted into that solution of potential sources of inspiration.