Collection
AI coding
Updated 16h
Collection
Updated 16h
How AI assistance impacts the formation of coding skills
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
First impressions: Delta - Cameron's writing
A look at Zed's new agent development tool.
Introducing Delta
From the Zed Blog: A multiplayer environment for coding with agents, from the creators of Zed.
On genAI: Was prototyping really a bottleneck?
I keep hearing folks claim that the fact we can ‘prototype’ so quickly now is a good thing (thanks to modern genAI). But what if the slow parts about prototyping are actually what make it worth doing?
108 PRs in eight days: Accidentally discovering loop engineering | Brittany Ellich | Offprint
How I shipped 108 PRs in eight days with an agent working my task board: the loop engineering setup, constraints, and lessons that made it work.
Primitive | Decision infrastructure for AI agents
Primitive captures your decisions as you build, shares them with your team, and holds your agents to them.
Hermes Workspace · Your AI agent’s command center
Chat, memory, skills, terminal, and files — one interface for everything your agent does.
Control the ideas, not the code - <antirez>
Agentic Coding is a Trap | Lars Faye
Remaining vigilant about cognitive debt and atrophy.
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.
When AI builds itself
Our progress toward recursive self-improvement, and its implications.
Apps and programming: two accidental tyrannies
On coding agents, malleable software, and the future of interface invention
I think Anthropic and OpenAI have found product-market fit
Anthropic are strongly rumored to be about to have their first profitable quarter. Stories are circulating of companies surprised at how expensive their LLM bills are becoming from usage by …
magarcia/cc2md
Convert Claude Code session logs into clean, readable markdown — with an interactive picker, terminal rendering, and GFM export.
paraschopra/make-pages-interactive
Contribute to paraschopra/make-pages-interactive development by creating an account on GitHub.
My impression is that AI coding is on a "pick two of three" triangle: scope, ship speed, and correctness. Small tools are (speed + correctness) fast prototypes are (speed + scope) and big projects are (scope + correctness). Every project that tries to be all three degrades to "fast prototype."
