Where Jev Fits in Software Workflows
A source-backed look at Jev through TypeSafe's writing, developer experiments, and awesome-jev projects: browser actions, model routing, triage, citation checking, context management, and deployment boundaries.
AI Engineer · Independent Thinker
Remy (Redreamality)
Building with AI agents, and thinking out loud — projects, writing, talks, and reflections in one place.
Visuals
View all visualsInteractive explainer
How Price and Volume Work Together
Read price and volume as contextual evidence about participation, liquidity, and market response—not as a certain trading signal.
Explore the visualInteractive explainer
How Air Conditioners Work
Follow the refrigerant through evaporation, compression, condensation, and expansion to see how an air conditioner moves heat outdoors.
Explore the visualInteractive explainer
What Is Loop Engineering?
Learn Loop Engineering in plain language: contracts, bounded attempts, evidence, durable state, budgets, stop routes, human review, and system improvement.
Explore the visualInteractive explainer
How Typhoons Form
Thirteen interactive steps explain how a warm ocean disturbance becomes an organized tropical cyclone.
Explore the visualRecent Blog Posts
View allCordis Explained: Spatiotemporal Composability, Plugin Systems, and DeepSeek Harness
A practical, evidence-based guide to Cordis, spatiotemporal composability, revertible effects, reactive coeffects, plugin lifecycles, and the architecture of DeepSeek Harness.
OpenSpec 1.5 Explained: Stores Beta, Explore-first Workflow, and Team-scale Spec Collaboration
A detailed update and usage guide for OpenSpec 1.5.0, covering Stores Beta, /opsx:explore, brownfield adoption, command frontmatter fixes, and the shift from repo-local specs to shared planning context.
OpenSpec Tutorial: CLI Install, Commands, AGENTS.md, and Real-World Examples
A practical OpenSpec tutorial for AI-native spec-driven development: install the CLI, initialize a project, create changes, validate specs, use AGENTS.md, and follow a brownfield workflow.
Monopoly + Addiction: Inside Lin Yuan's Investment Framework (China's Most Stubborn Value Investor)
A deep dive into Lin Yuan — the doctor-turned-fund-manager dubbed "China's Buffett" — and the three-pillar framework (industry direction + monopoly + addiction) behind a 23%+ annualized 10-year track record.
From Busy Beaver to Modern CPUs: How a 1936 Abstraction Became Real Silicon
A guided tour from Tibor Radó's Busy Beaver function to the von Neumann architecture, showing how the Turing machine's four conceptual primitives — tape, head, state, transition — were engineered into the CPU, memory hierarchy, and instruction sets of every computer you use today.
What If Humans No Longer Need to Work: A Four-Dimensional Deduction and Dividend Map
A multi-agent thought experiment on post-work society — across economic, psychological, social, and civilizational dimensions — and where the transition-period dividends actually sit.
CLAUDE.md and AGENTS.md, In Depth: From Basics to Counterintuitive Patterns
From Anthropic's official guidance to Karpathy's program.md paradigm, from the two-strikes rule to Darwinian memory, from Spec-Driven to Eval-Driven — a long-form survey of how we write project files for AI coding agents, and the counterintuitive mental models worth borrowing.
Mapping the DeepSeek V4 Evaluation Suite: A Field Guide to 2026 LLM Benchmarks
A complete walkthrough of every benchmark DeepSeek V4 reports against — from LiveCodeBench to SWE-bench Pro to the ClawBench family — and what each one actually measures.
The Person Behind the Curtain: The Wizard of Oz Method in UX
How to validate complex product ideas — especially AI-driven ones — before writing a single line of code, by borrowing a trick from a children's fairy tale.
The Agent Harness Pattern: Lessons from Claude Code's Core Loop
What makes a production agent loop survive the real world? We extract the Agent Harness Pattern from Claude Code's source — a generalizable blueprint for building resilient, self-recovering AI agent runtimes.
Claude Code Leak: A Deep Dive into Anthropic's AI Coding Agent Architecture
Claude Code's source was briefly exposed. We read all 1,884 TypeScript files. Here is what the architecture reveals about where AI coding tools are actually heading.
From the Meditations
View allThe Model's Hourly Wage: Why Token Pricing Is Not Enough
Once models begin occupying human waiting time, token pricing no longer explains their real cost. A model's hourly wage brings price, latency, caching, and task productivity into one unit-economics framework.
AI and labor
Why a Section Called Meditations
The blog records what I've learned; Meditations records what I've come to understand — why this section exists.
origins
Recent Talks
View allMulti-Agent Systems: From Theory to Practice
Multi-agent systems, from fundamentals to practical implementation
Online Presentation
Quantitative Trading Strategies: Insights and Practical Experience
Sharing fundamental quantitative trading strategies and practical implementation experience
Online Technical Sharing Session
Recent Questions
View allWhy is Augment Code worth $1 billion?
A breakdown of Augment Code's user base, pricing, funding, and — most tellingly — its investor roster, which reveals the company's real strategic bet.
How are different timeframes connected in price action?
A simple but rigorous way to think about multi-timeframe analysis without contradictions
How do you define a trend?
A clear definition of trend that works across charting and quantitative statistics
How do you define a swing in trading?
A practical definition of swings (price waves) that makes sense for discretionary and quant systems
How do you define market structure?
Turning price action into a consistent framework: pivots, breaks, ranges, and state changes
How to understand 'profit and loss come from the same source' (盈亏同源)?
Why every trading edge has a matching failure mode, and how to use that fact to design risk and diversification
Chaos (Signals)
View allThe Emmy as Summer Festival: How Widow's Bay Remade the Map at the 78th Primetimes
Apple's haunted-island comedy did not just win Comedy Series at the 78th Emmys. It exposed an Academy chasing discovery dopamine, while HBO Max kept the institutional crowns and Netflix left with actors but no banner series.
AI Agents Are Becoming a New Kind of Personal Computer
NVIDIA's March 16-17, 2026 GTC messaging around NemoClaw, OpenClaw, and OpenShell argues that private, always-on local agents could define the next personal computing cycle.
Telecom Networks Want To Become the Distributed Inference Layer for AI
NVIDIA's March 17, 2026 telecom AI grid push reframes carriers as the next edge inference platform, where latency, data locality, and cost per token become network architecture questions.
AWS Wants Agent Building To Have A Package Layer, Not Just A Prompt Layer
AWS's AI Registry for Agents spec suggests the next battle in the agent stack may be about packaging, distribution, and reproducible installs rather than model access alone.
GitLab Duo Agent Platform + MCP: GitLab Wants To Be the Operating System for AI Coding Agents
GitLab is pushing AI coding beyond copilots and into governed workflow infrastructure, with external agents, managed credentials, audit trails, and MCP connections across the DevSecOps stack.
Cloudflare Is Rebuilding Web Errors for AI Agents, Not Just Browsers
Cloudflare is pushing RFC 9457 problem details into the agent era. That matters because AI workflows need machine-readable failures, not decorative HTML error pages.
Reading Notes
View allOpenSpec Deep Dive: Spec-Driven Development Architecture & Practice in AI-Assisted Programming
Explore OpenSpec's core architecture, workflows, and enterprise applications to understand how Spec-Driven Development solves context loss and hallucination in AI programming
BMAD-METHOD Guide: Breakthrough Agile AI-Driven Development
A comprehensive analysis of BMAD-METHOD's core architecture, deployment, agent roles, and four-phase agile methodology for mastering spec-driven AI development
GitHub Spec Kit Deep Dive: AI-Driven Specification Development Methodology
An in-depth analysis of GitHub Spec Kit's architecture, workflows, and enterprise applications exploring how Spec-Driven Development solves context loss in AI programming
Notes on 'Deep Work' by Cal Newport
Key insights and takeaways from Cal Newport's book on focused work