I think this is a creative approach. I wonder how the success rates for that little RNN compare to the success rates of the primary LLM, especially for complex queries or complex tool calls. At some point you have to scale that network up large enough to get better results. Eventually you've come back around and you might as well use an LLM. I think a similar approach with potentially better results (depends on the application) could be accomplished by using that same dataset to finetune a small language model. It'd be interesting to see some success rate comparisons.
Is it realistic to think that the poors will start their own economy servicing each other? I'm sure there would be chaos and violence for a period but eventually it seems like the path upward would be a whole new economic system for that 98%. This system could even make use of the automation offered by AI.
Do something to help everyone else stuck in the system. Hire lobbyists to improve healthcare in the US. All the other rich people are just trying to make things worse and extract as much as possible.
"Our AI agent finds precisely what you ask for, 10-50x better than Google Scholar"
I was curious how this was measured since benchmarking accuracy for LLMs is tough. Found this in the paper:
"This classification accuracy was benchmarked by manually analyzing over 400 papers across a range of representative searches, and comparing the human evaluation to the language model’s judgment"
I'm skeptical that their dataset of 400 papers with 3 classification labels (highly relevant, closely related, or ignorable) is large enough to represent the diversity of queries they're going to get from users. To be clear, I don't think this undermine's (haha) the value of what they've built, still very cool.