2026
-
Crafting Interpreters (III): Resolving a Name Before It Runs
Resolver freezes variable identity before execution: each variable-use node gets either a fixed local depth or a deliberate global lookup, so mutable closure environments can change without changing lexical binding.
-
Crafting Interpreters (IV): Resolver Lays the Track, Interpreter Fills the Values
jlox's object system stays inside the same runtime model: classes, instances, methods, this, inheritance, and super are built from LoxClass, LoxInstance, LoxFunction, environments, closures, and resolver distances.
-
Crafting Interpreters (II): The Tree Begins to Run
An AST becomes a run when the interpreter walks it: expressions produce values, statements create effects, environments hold state, control flow chooses subtrees, and closures preserve captured scope.
-
Crafting Interpreters (I): When Source Text Becomes Structure
Source text becomes executable structure in phases: scanning creates token boundaries, parsing turns precedence and associativity into an AST, and later phases consume that preserved tree.
-
Codex Source Dive (VI): Context Engineering
Codex context is a managed runtime surface: AGENTS.md, skills, thread history, compaction, and runtime settings each have ownership rules that let long-running work survive.
-
Codex Source Dive (V): The Security Model
Codex security is a layered execution membrane: sandboxing defines the technical boundary, approvals decide review, exec policy classifies command risk, and OS backends enforce the result.
-
Codex Source Dive (IV): The Tool Runtime
Codex tools are model-visible schemas backed by a policy-bound runtime that routes shell commands, patches, MCP, skills, permissions, sandboxing, streams, and history through one managed execution path.
-
MiniMax Sparse Attention: Teaching Long-Context Models to Use an Index
MiniMax Sparse Attention turns long context into searchable memory: a learned index selects relevant key-value blocks, then exact softmax attention reads only those blocks.