Storage Nightmare: A CH car profile for a region can be massive (e.g., OSRM's Europe is tens of GBs, their global car profile around 200GB for just one profile). Our goal was to keep all profiles and parameters for the entire planet well under 20GB.
Can these agent-benchmaxxed implementations actually beat the existing machine learning algorithm libraries, despite those libraries already being written in a low-level language such as C/C++/Fortran? Here are the results on my personal MacBook Pro comparing the CPU benchmarks of the Rust implementations of various computationally intensive ML algorithms to their respective popular implementations, where the agentic Rust results are within similarity tolerance with the battle-tested implementations and Python packages are compared against the Python bindings of the agent-coded Rust packages:
，详情可参考51吃瓜
"You can do anything from your bedroom. And I don't think that's a bad thing."
"This was really an "oh my God" moment," says the scientist behind the findings, Dr Peter Fretwell at British Antarctic Survey, who has worked on Emperor penguins for 20 years.