Search

Said and published

• Guillermo Rauch x.com 3 Sept Run ▲ ~/ vercel ai-gateway coding-agents setup Points all coding agents to AI Gateway, getting you 100% uptime, observability, budgets, and ease of switching.
• Simon Willison Blog 5 Sept Using Blender with coding agents on macOS
• Bruce Schneier Blog 4 Sept AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
• Tobias Lütke GitHub 22 Aug reve — The directory is the agent: durable Ruby coding agents in mandatory microsandbox microVMs
• Gergely Orosz Newsletter 25 Aug Why Ramp built its own in-house coding agent, Inspect
• Simon Willison Korrent 8 Aug Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. I REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet
• Ivan Santos GitHub 6 Sept dotfiles — pragmaticivan's personal configurations
• Adam Tornhill x.com 3 Sept The main difference with AI coding is that I no longer focus on individual building blocks. Rather, agents allow me to iterate on the whole system at the feature level. That characteristic is where the bulk of agentic…
• Russ Cox GitHub 19 Aug agent — Agent helpers
• Tobias Lütke Korrent 25 Aug Coding agents should read the shared AGENTS.md convention; insisting on a tool-specific CLAUDE.md creates split-brain problems across a team. I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc. Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team…
• Sebastian Raschka Newsletter 27 Jun Using Local Coding Agents
• Thomas Ptacek Korrent 19 Aug Coding agents make every plugin interface you ever blew off trivially usable, which is a large productivity win. I can't say enough how excellent a coding agent is at customizing Chrome with extensions. A huge productivity win. Every plugin interface you've ever blown off is now trivially usable.
• Andrew Chen x.com 24 Aug lazymaxxing agentic coding: When i have multiple agents working on the same code repo, if there's conflicts/overlaps, they just figure it out amongst themselves? I want to have 8 tabs going on new features, and the…
• Elio Struyf GitHub 4 Sept vscode-agent-frame — See which of your coding agents are working, waiting, or idle at a glance — Agent Frame colors the VS Code window to match.
• Tobias Lütke GitHub 31 Aug wrap — Run coding agents and project commands inside isolated Arch Linux microVMs
• Gergely Orosz x.com 29 Aug It’s a weird complaint to have but with AI agents, that “flow state” during coding is gone (because the coding itself is gone.) Every time I talk with a dev about work now vs before, it seems to come up, like today with…
• Sebastian Raschka GitHub 7 Apr mini-coding-agent — Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
• Pieter Levels Korrent 28 Jun AI agents and AI coding will run on servers and from the cloud first, not on your laptop. …@karpathy with Claude moving to the cloud (via Slack etc), I think AI "agents" and AI coding will operate on servers / from the cloud…
• Sebastian Raschka Newsletter 4 Apr Components of A Coding Agent
• Varun Raj Manoharan GitHub 27 Jul changelog-plugin — Prompts your coding agent for a CHANGELOG.md entry whenever you open a pull request.
• Terence Tao Blog 14 Jul Visualizing the Gilbreath expectation sequence
• Dean W. Ball Newsletter 8 Jan Among the Agents
• Federico Viticci Blog 30 Jun Headless Macs and Hamstrung iPads
• Terence Tao Blog 17 Jul Two more apps: visualizing the zeta process and the motions of the heavens
• Manassarn "Noom" Manoonchai GitHub 12 Aug slidev-ai-template — A minimal Slidev starter, pre-wired for AI coding agents (per sli.dev/guide/work-with-ai) so you can fork it and have an agent write your slides for you. A bare Slidev project —…
• Jason Liu Site 11 Sept 2025 Coding Agents Speaker Series: Lessons from Industry Leaders
• Lex Fridman Podcast 1 Feb #490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI
• Naval Ravikant Site 28 Apr A Return to Code
• Lex Fridman YouTube 31 Jan State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
• Luke Wroblewski Korrent 7 Apr Designers should code, and AI coding agents have reopened that door after a decade in which front-end complexity closed it. …of front-end development made it impractical for most. Thankfully, AI coding agents have reopened the…
• Sunil Pai Korrent 14 Aug Coding agents made implementation cheap without making roadmaps shorter or software better -- the binding constraint was never how fast code gets written. buuuut my roadmap is’nt ten times shorter. and I’m definitely not ten times better at deciding what is worth building. teams haven’t started casually shipping a year of product work every month. you can look around and…
• Mario Zechner Blog 15 Aug 2025 MCP vs CLI: Benchmarking Tools for Coding Agents
• Sunil Pai Blog 3 Jan where good ideas come from (for coding agents)
• Lex Fridman x.com 26 Aug …0:00 - Episode highlight 1:27 - Introduction 2:56 - Programming with AI agents 18:14 - How software will change 27:30 - AI impact on open source 37:21 - Building Omarchy Linux distro 47:05 - Vibe coding vs agentic…
• Sunil Pai Blog 7 Jan the context is the work (what the day-to-day looks like now)
• Peter Steinberger Blog 14 Oct 2025 Just Talk To It - the no-bs Way of Agentic Engineering
• Eugene Yan x.com 18 Feb Sonnet 4.6 is a big upgrade over 4.5. And it has 1M context! It's also versatile across classification, coding, computer use, autonomous agents by adjusting effort and thinking modes.
• Jason Liu GitHub 16 Jan presentations — A Slidev-based presentation starter kit with a deck-based structure for creating and managing multiple presentations. This setup is designed to be easily used with coding agents - the…
• Jason Liu Site 11 Sept 2025 Why Cognition does not use multi-agent systems
• Simon Willison Korrent 31 Dec 2025 MCP may turn out to be a one-year wonder, because coding agents that can run arbitrary shell commands make Bash the best general-purpose tool interface. The reason I think MCP may be a one-year wonder is the stratospheric growth of coding agents. It appears that the best possible tool for any situation is Bash—if your agent can run arbitrary shell commands, it can do…
• Jason Liu Site 11 Sept 2025 Why Grep Beat Embeddings in Our SWE-Bench Agent (Lessons from Augment)
• Hamel Husain Site 2 Mar Evals Skills for Coding Agents
• Luke Wroblewski Korrent 7 Apr The loop has flipped: it used to be faster to mock up software than to ship it, and now designers can work iteratively in production code. For years, it was faster to mock up software than to ship it. Designers stayed "ahead" of engineering with prototypes. Now AI coding agents make development so much faster that the loop has flipped.
• Hamel Husain GitHub 9 Mar hamelnb — Coding agents write entire scripts in one shot, then debug from the top when something breaks. That works sometimes, but you might not always want to do it that way -- try a small piece, ch…
• Simon Willison Korrent 31 Dec 2025 Running coding agents without approval prompts is a normalization-of-deviance risk: the fact that it has not caused a disaster yet is itself the problem. I run in YOLO mode all the time, despite being deeply aware of the risks involved. It hasn’t burned me yet... ... and that’s the problem.
• Hamel Husain GitHub 27 Feb research-council — A Claude Code plugin that orchestrates deep research across two coding agents — Claude Code and Codex CLI (OpenAI) — running in parallel with cross-pollination refinement and final…
• Luke Wroblewski Korrent 19 Jan Design deliverables are no longer static assets or guidelines but tools: custom software that generates on-brand assets on demand. But with today's AI coding agents, building software is remarkably easy. So instead of handing over static assets and static guidelines, designers can deliver custom software. Tools that let clients create their own…
• Adam Tornhill x.com 25 May I still meet people convinced that AI coding tools will soon reach a point where code quality, design, and even architecture are "solved". So I ran a small ad-hoc experiment. I’ve been working on a CLI tool and let…
• Mario Zechner Korrent 25 Mar The human bottleneck is a safety property: remove it and small, individually harmless coding errors compound at a rate nobody feels until it is too late. With an orchestrated army of agents, there is no bottleneck, no human pain. These tiny little harmless booboos suddenly compound at a rate that's unsustainable. You have removed yourself from the loop, so you don't even…
• Peter Steinberger Korrent 12 Feb Working with coding agents is a skill you learn like an instrument; judging the tools after one try is like calling a piano bad after one go. It's the same way as you have to play with a guitar before you can make good music. It's, it's not, oh, I, I touch it once and it just flows off. It, it's a, it's a, a skill that you have to learn like any other skill.