Featured essay
Attention Should Be Allowed to Say No
Qwen's Gated Attention separates where an attention head reads from whether its output should influence the model.
Read essay ↗All writing
2 entriesAgentic systemsEssay · Reliable agents
The Case for Planner–Executor Architectures in Agentic Coding
Why serious coding agents should separate judgment from execution—and spend frontier-model capability where it matters most.
7 min read
Attention & modelsInteractive lab · Modern attention
Attention Lab: Eight Ways a Model Looks
Interactive field guides to the attention mechanisms shaping modern language models.
Explore