FrontierCS: Evolving Challenges for Evolving Intelligence
An open-ended benchmark for evolving computer science challenges with objective and fine-grained evaluation of agent capabilities.
Posts
newest first
Introduction to Claude Code and Codex
A practical introduction focusing on Claude Code and Codex, with clear explanations of memory, permissions, MCP, custom commands, and best practices for dual-tool collaboration.
ODE Perspective on Neural Networks
We cover the neural ODE perspective in terms of optimization and architecture design.
View Transformer Layers from Online Optimization Perspective
We cover mesa-optimization, test-time-training (TTT), and a broad view of fast weight programming in transformer models.
What is the Intrinsic Dimension of Your Data?
We introduce the concept of intrinsic dimension and provide a method to estimate it. It is amazing that ImageNet has only 50 of the intrinsic dimension.
Bridging the Parallel Decoding of LLMs with the Diffusion Process
We introduce Jacobi Decoding, a parallel decoding algorithm for LLMs, and its connection to the diffusion process in terms of high-level concepts.