Category: systems
-
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.
-
Codex Source Dive (I): the agentic loop is a runtime boundary
TLDR: A Codex turn is not one model call. It is a managed execution window where user input, tool calls, tool results, cancellation, compaction, and final answers are ordered by the runtime.
-
Codex Source Dive (II): goals are runtime state, not prompts
TLDR: A Codex Goal is a thread-level long-running task state machine. It stores objective, status, budget, usage, resume state, and continuation gates instead of relying on one remembered prompt.
-
Codex Source Dive (III): subagents are a thread tree
TLDR: A Codex subagent is not a background model call. It is a persistent child thread with identity, inherited runtime policy, forked context, mailbox communication, capacity limits, and resume behavior.
-
The Mythical Man-Month: Chapters 13-End
TLDR: In the second half of The Mythical Man-Month, Brooks closes the argument around integration, milestones, documentation, no silver bullet, incremental development, and the architect role.
-
The Lego work method: simplicity is an operating discipline
TLDR: The useful lesson from Lego is not a slogan about creativity. It is an operating discipline: stay close to the customer, keep accountability internal, reduce complexity, and make execution visible.