OptionProbability
It won't be
Giving all LLMs access to the internet and databases of scientific papers
Other
Bigger model trained on more data + RL
Vector Embeddings (as with Pinecone https://www.pinecone.io/)
Filtering (as with Deepmind AlphaCode https://www.deepmind.com/blog/competitive-programming-with-alphacode)
Vigger models + prompt engineering
Joint Embedding Predictive Architecture (https://arxiv.org/pdf/2301.08243.pdf)
Feed Forward Algorithms (https://www.cs.toronto.edu/~hinton/FFA13.pdf)
Ensemble Combined with Fine Tuning
46
20
10
9
8
2
1
0
OptionVotes
YES
NO
139
111
