Elegant object matching from several viewpoints

Model routing can finally be a design choice rather than a system enhancement

From guarding one agent to steering a fleet

A model can recall a fact in the direction it learned it and fail in the other. Here's a toy version of why

Trying to answer the question of "Can LLM agents discover?" through the lens of creativity

A from-scratch PyTorch build that recovers blood flow, viscosity, and wall shear stress in a narrowed artery from 40 noisy velocity readings

Coordinating agent capability development with the application it powers

Giving an LLM permission to act, in 9 steps

A theoretical advantage that didn't survive contact with a real benchmark.