Search papers, labs, and topics across Lattice.
3
0
5
2
Harness-assisted data synthesis boosts LLM forecasting performance by reducing temporal leakage and increasing sampling efficiency, leading to superior predictive capabilities.
Attribution regularization can dramatically improve model robustness to geometric transformations with minimal impact on accuracy.
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
