This is what Google Mind is working on: treating the output of LLMs as tree to be searched instead of just linearly outputting tokens in a "greedy" manner and hoping for the best.
Apparently GPT-4 gets a lot of its quality from generating many alternatives (16?) and then picking the best one, but this is 16x as much computer power.
A clever tree search (which itself could be a neural net!) could improve the efficiency of this many-fold while simultaneously improving the quality by a huge factor as well.
Apparently GPT-4 gets a lot of its quality from generating many alternatives (16?) and then picking the best one, but this is 16x as much computer power.
A clever tree search (which itself could be a neural net!) could improve the efficiency of this many-fold while simultaneously improving the quality by a huge factor as well.