Skip to content

Blog

Writing

Causal analysis you can argue with.

Posts are structured around variables, counterfactuals, mechanisms, and interventions — with explicit uncertainty and falsification ideas.

Latest

2026-01-17 · ~16 min · tags: causality, agent-memory, knowledge-graphs

Temporal Memory Beats Bigger Context

Temporal knowledge graphs turn memory into a governed, time-aware system—reducing stale-context errors and making agent behavior auditable, not mystical.

Coming next

A growing feed

This index is designed to scale. As new posts are generated, we add them here in chronological order with a one-line description and consistent metadata.

For topic-based entry points, use Topics and site search.

Feed format (for future posts)

Each post should include stable front matter fields so the archive stays uniform: title, date, description, tags, reading_time_minutes.

Recommended discovery pattern: this page for chronology, Topics for curation, and global search for everything else.

Note: posts are intentionally not listed one-by-one in the site navigation. The feed, tags, and search are the primary discovery mechanisms.

All posts (chronological)

Date Post Notes
2026-01-17 Temporal Memory Beats Bigger Context Temporal validity, supersession, hybrid retrieval, governance
2026-01-17 Mechanism-Executable Causal GraphRAG Executable clauses, EMCT primitives, governance loop, interventions
2026-01-17 HRM’s Latent Reasoning Still Needs Verification Adaptive depth, latent reasoning, harness verification, deployment risk
2026-01-17 Agent Memory Needs Identity, Governance, and Decay Identity, temporal validity, provenance, decay, governance
2026-01-17 AI Coding Assistants: A Causal Framework for Productivity and Risk Harness vs model, tests, measurement, Goodhart loops
2026-01-17 From SWOT to Testable Causal Hypotheses Translate narrative into falsifiable mechanisms + governance
2026-01-16 Why Small Frictions Cascade into System Failure Mechanisms, feedback loops, leverage points

Where to start

How to Read Posts

A quick map of the structure: model → diagrams → evidence → interventions.

Topics

Curated entry points that scale better than a huge navigation tree.

Reasoners

If you want the infrastructure behind the writing, start here.