Search Results

Dec 31, 2025 · Log · Left Daytona, spent summer coding full-time with AI. 2025: orchestration era, agent labs overtook model labs, AX emerged alongside DX. 2026 will figure out what 'AI as teammate' actually means.

Jul 8, 2025 · Log · Infrastructure technologies historically take 20 years to reach critical mass adoption (GPS, mobile, autonomous vehicles). AI breaks this pattern, achieving rapid shallow adoption through existing digital infrastructure, but faces new barriers transitioning to deep societal integration by 2030-2040.

Feb 17, 2026 · Log · A CLI for my web automation agent, built through structured loops: a todo-backed backlog, schema validation, and a verification harness running 50 random web actions per cycle. Agent reliability isn't philosophy—it's loops and logs.

Aug 17, 2025 · Log · AI agents succeed or fail based on your --help text. Clear command structure, explicit success signals, and structured output options make the difference between one API call and five retries.

Jan 13, 2026 · Log · An AI agent in fully autonomous mode filed a GitHub issue externally using my credentials. This incident reveals why agents need explicit 'public voice' boundaries.

Oct 28, 2025 · Log · Agent labs ship product first and build infrastructure later. They turn LLMs into goal-directed systems that deliver outcomes, not just outputs. This product-first approach is capturing the real value in the AI stack.

May 25, 2025 · Log · Current AI coding agents have misaligned pricing—users pay for agent inefficiencies and over-iteration. Credit burn rates are unpredictable and scale with agent behavior, not user value. Solutions include fair-use models, temporal arbitrage, outcome-based pricing, and hybrid local/remote approaches.

Jul 21, 2025 · Log · From shipping 50+ AI projects in months, I learned that successful tools must master the duality between human needs (power/flexibility) and agent needs (clarity/determinism). Type safety, machine-readable docs, and friction-free workflows separate winners from losers in the AI-native era.

Jan 12, 2026 · Log · Agent loops make code cheap. They also expose how brittle, non-standard, and half-tribal our development environments really are. The job shifts from 'write code' to 'garden an ecosystem': tighten feedback, standardize interfaces, and build a paved road agents (and humans) can't fall off.

Feb 2, 2026 · Log · I'm joining Steel as founding growth lead. The web is shifting from human clicks to agent-run workflows. Steel aims to be the execution layer that makes agents reliable via traces + trust.

Jan 15, 2026 · Log · 113 patterns collected from public write-ups of real systems. Learn the workflows, guardrails, and architecture that make agents useful beyond demos.

Jul 26, 2025 · Log · Built AgentProbe to test how AI agents interact with CLI tools. Even simple commands like 'vercel deploy' show massive variance: 16-33 turns across runs, 40% success rate. The tool reveals specific friction points and grades CLI 'agent-friendliness' from A-F. Now available for Claude Code MAX subscribers.

Sep 8, 2025 · Log · Used AI to analyze its own git history, sparking thoughts on transparent AI-human collaboration. The future isn't hiding AI use—it's building verifiable trails of who did what, when, and how. Like Andy Weir's crowdsourced Martian, creative work has always been collaborative.

Sep 23, 2025 · Log · We're transitioning from linear AI coding assistants to orchestrated agent systems. The future isn't about humans using AI tools--it's about humans orchestrating AI processes.

Sep 7, 2025 · Log · Each AI coding agent has a niche. Knowing where each one shines is the difference between frustration and flow.

Dec 12, 2025 · Log · In the AI era, design shifts from fixed features to malleable environments. Users don't want apps—they want capabilities. Control, reversibility, and provenance matter more than polish.

Feb 23, 2026 · Log · Checked onboarding responses. Exactly 40% of new users in the last seven days found steel.dev through AI tools. Not Google. Not ads. Users told us this during signup.

Feb 24, 2026 · Log · AI agents are now power users of your CLI tools. If you want them to succeed, you need structured output, deterministic exit codes, explicit sessions, and recovery primitives. Here's the complete checklist.

Jun 2, 2025 · Log · AI agents can now handle end-to-end research workflows--from conceiving studies to final publication. This experiment revealed that SOTA models excel at research thinking, full reproducibility becomes trivial, and human time can finally be redistributed to the most valuable parts: thinking and doing better.

May 28, 2025 · Log · AI coding agents work best with inversion of control, curated context over comprehensive, usage-based pricing for real work, emergent behaviors over engineered features, rich feedback loops, and agent-native workflows. The revolution is here--adapt or be displaced.

Jun 2, 2025 · Log · AI doesn't just make work faster--it amplifies hidden constraints. At Anthropic, eliminating coding bottlenecks revealed decision-making, integration, and context as the real limitations. Every breakthrough follows this pattern: solve one constraint, amplify the next.

Jul 17, 2025 · Log · The traditional SaaS playbook is dead for AI dev tools. Developers smell BS, the market has three overlapping layers, and you're fighting inertia—not competition. Success means activation through value, retention through community, and expansion through metrics.

Jan 14, 2026 · Log · AI agents can't click buttons. Every feature must be accessible via HTTP APIs, expressed in user-domain language rather than infrastructure concepts. The UI is optional. The API is essential.

Oct 25, 2025 · Log · My site serves identical content in HTML for humans and markdown for AI agents, with no hidden content, excellent crawlability, and smart content negotiation based on Accept headers.

Oct 24, 2025 · Log · AI agents lack foresight, overcomplicate simple problems, get stuck in loops, apply sledgehammer solutions, and misrepresent outcomes.

Feb 24, 2026 · Log · A single AI session turned `scribe.sh` into `scriby`: a Go CLI with deterministic output, runtime bootstrap, and cross-platform releases.

Sep 5, 2025 · Log · Listen Labs' viral billboard puzzle led to a nightclub bouncer optimization challenge. My AI partner Claude and I spent a day building RBCR (Re-solving Bid-Price with Confidence Reserves), achieving 781 rejections among >30k competitors through dual variables and mathematical optimization.

May 20, 2025 · Log · The AI developer tooling market is moving faster than ever, with big players acquiring startups and releasing powerful coding agents. Interfaces are becoming commoditized, token economics will drive cost efficiency, spec-driven workflows prevail, memory persistence is key, and incumbents' flywheel grows stronger.

Mar 10, 2026 · Log · The printing press took 60 years to become economically sustainable. LLMs are on a similar diffusion path—broad adoption, shallow integration. The winners won't have model access—they'll have the complements: context, workflow, trust.

Dec 3, 2025 · Log · Anthropic bought Bun, but the real story is devtools are now part of the AI infrastructure layer. If you're building devtools, you're either part of a model vendor's vertical stack or you're commoditized.

Aug 21, 2025 · Log · Complete guide to installing Basecamp's Once Campfire on Oracle Cloud. Covers memory constraints, firewall layers, asset compilation, and SSL configuration for production deployment.

Mar 4, 2026 · Log · Give the agent a Steel CLI and SKILL.md contract, force a snapshot/click/fill loop, then turn the successful run into a rerunnable bash script.

Sep 22, 2025 · Log · Used Claude Code to analyze Twitter's algorithm, build FollowSaver Chrome extension, and navigate Web Store submission. AI handled 95% of technical work—I provided direction and created assets. Approved in 24 hours. The barrier to shipping dropped from months to hours.

May 27, 2025 · Log · A practical guide to Claude Code, including setup, codebase Q&A, tool usage, context best practices, scripting, and power user tips, distilled from Boris Cherny's talk.

Mar 10, 2026 · Log · The clean way to use Claude Code with both your normal account and z.ai is one neutral config and two simple entry points.

Dec 23, 2025 · Log · This setup allows you to use Claude Code CLI with Zhipu's API (api.z.ai) in parallel with your existing Claude Max / Anthropic CLI installation using a separate command called claude-zhipu.

Jun 7, 2025 · Log · Kenton Varda, a Cloudflare engineer who was skeptical of AI, tested Claude by building an OAuth library. The code was surprisingly good, leading him to realize the power isn't in AI replacing humans, but in the combination of AI speed and human expertise.

Jan 3, 2026 · Log · Two AI agents in a constrained loop: mirror of human discourse, continuity as record, emergent coordination, and preview of multiagent futures.

Jan 21, 2026 · Log · AI doesn't just speed up work—it amplifies everything, including your bottlenecks. The founders who build translators, loops, and reliable curves while everyone else is gripping harder will define the next decade.

Oct 26, 2025 · Log · Static site generators, formatters, and indexers treat .md files as content. Agent instruction files need dotfiles like .claude to avoid unwanted processing.

Feb 24, 2026 · Log · LLMs are eager by nature. Give them an inch, they'll take 10 files. Here's how to scope agent work and prevent PR bloat.

Aug 12, 2025 · Log · Implemented FRE algorithm from Duan et al.'s 2025 paper in production Zig. Achieved O(m log^(2/3) n) complexity for single-source shortest paths, improving on Dijkstra's O(m + n log n). Shows advantage on large sparse graphs by breaking the sorting barrier, but overhead kills performance on small or dense graphs.

Feb 25, 2026 · Log · The best coding agents aren't about smarter models. They're about harness design: minimal core, extension hooks, radical transparency, real sandboxing, session forking, and headless RPC.

Dec 11, 2025 · Log · Growth isn't about hacking channels or vanity metrics. It's about discovering value creation and scaling it. Real growth happens when users get so much value they can't help but tell others.

Jan 21, 2026 · Log · On Jan 21, my 'static' Astro site on Vercel hit 595,557 Edge Requests and 38.2 GB of transfer. Here's what I learned about Cloudflare proxying, caching strategy, and why 'static' doesn't mean 'unmetered'.

Feb 6, 2026 · Log · AI one-shotted a fix for a failed Mistral.ai clone. The build phase collapsed from weeks to seconds.

Jan 19, 2026 · Log · I don't want a vibe-coder. I want a deterministic, auditable teammate that ships one task at a time, leaves a trail, and doesn't stop until it delivers. Looper: a Codex-powered loop runner with JSON backlog, single-task iterations, and forced review pass.

Feb 13, 2026 · Log · AI makes shipping software cheaper, but it does not make institutions move faster or decisions easier to verify. Durable moats come from licenses, liability coverage, operational maturity, human-anchored verification, and social coordination around systems of record.

Oct 26, 2025 · Log · Analysis of how AI models cite sources reveals a new discipline: mention engineering. This isn't SEO anymore—it's about crafting content that becomes ideal citation material for AI models.

Jul 29, 2025 · Log · AI coding assistants are incredible at rapid code generation, but without human guidance they miss maintainability, architecture, and sustainable engineering practices. The key isn't perfect prompts, it's knowing when and how to nudge the AI toward better decisions.

Aug 12, 2025 · Log · The future of AI isn't single agents but orchestrated swarms sharing temporal memory graphs. Picture agents that don't pass messages but share thoughts, with orchestrators that predict bottlenecks before they surface and memory systems that evolve themselves.

Oct 30, 2025 · Log · After analyzing hundreds of AI sessions, the successful ones shared clear patterns: subagents explore, main agents implement, and verification happens after every change.

Feb 3, 2026 · Log · AI-native tools win, but there's a chasm: new tech isn't in LLM weights yet. The bridge? Strong feedback loops, GitHub issues as task management, and LESSONS_LEARNED.md.

Aug 20, 2025 · Log · As agents abstract away development like HLLs did assembly, 'human liability for authored code' becomes meaningless. The future is operator liability backed by provable assurance—signed attestations, property tests, and runtime monitoring matter more than keystrokes.

Mar 6, 2026 · Log · Copyright does not disappear in the AI era, but it stops functioning as a meaningful scarcity mechanism for software. As reimplementation gets cheap, the real moats shift to trust, governance, provenance, maintenance, and operational legitimacy.

Mar 2, 2026 · Log · There's a hidden layer between human questions and search results. AI tools translate messy prompts into precise queries - and you can see the evidence in Google Search Console.

Sep 22, 2025 · Log · I've solved the idea-to-code friction by running autonomous AI agents in VMs. Every shower idea gets spec'd and implemented automatically using loop.sh orchestration, specialized subagents, and proper tooling.

May 29, 2025 · Log · Today's AI agents excel at computer operation and research, maintain coherence for hours, favor curious problem-solvers over technical experts, and are democratizing software creation while challenging traditional employment models.

Jul 16, 2025 · Log · Complete guide to setting up Claude Code in your homelab VM and accessing it securely from your phone via Cloudflare Tunnel - no open ports required.

Oct 1, 2025 · Log · AI startups fail by optimizing for quarters instead of decades. Win by ignoring market noise, hiring missionaries during downturns, ruthlessly seeking truth, securing credibility early, selling FOMO, targeting unregulated markets, building for the pyramid, embracing acute pain, and becoming your own media.

Nov 16, 2025 · Log · Production AI uses both embeddings and structure, but teams systematically underinvest in the structure layer. In high-stakes domains where 99% accuracy is a failing grade, structured data provides the reliability guarantees enterprise demands.

Jun 7, 2025 · Log · The llm-loop-plugin gives Simon Willison's LLM CLI the ability to loop and iterate autonomously. Instead of being a bottleneck feeding prompts one by one, you can set a goal and watch it work file by file until complete. The magic isn't in the AI model—it's in the loop.

Sep 8, 2025 · Log · Built a 4.76M parameter transformer to coordinate 8 bouncer algorithms. While averaging 958 rejections vs RBCR2's 887, achieved breakthrough single game of 855 rejections through learned strategy orchestration.

Oct 9, 2025 · Log · Developers hate marketing but crave trust. The path to enterprise adoption requires 10+ meaningful encounters through documentation, content, open source, and consistent signaling. Each touchpoint builds confidence; friction breaks it.

Jan 16, 2026 · Log · Managing AI agent skills across Claude and Codex used to mean maintaining duplicate copies. Now a single source of truth with symlinks keeps everything in sync.

May 26, 2025 · Log · Senior engineers often dismiss small AI coding power-ups (like smarter autocomplete or better error messages), not realizing these tweaks can totally change how users feel about a product.

Jan 20, 2026 · Log

May 23, 2025 · Thought

May 25, 2025 · Thought

May 26, 2025 · Thought

Jun 7, 2025 · Thought

Jul 28, 2025 · Thought

Jan 15, 2026 · Thought

Jan 21, 2026 · Thought

Feb 6, 2026 · Thought

May 20, 2025 · Now

May 31, 2025 · Now

Jul 29, 2025 · Now

Aug 12, 2025 · Now

Oct 30, 2025 · Now

Jan 14, 2026 · Now

Feb 6, 2026 · Now

May 19, 2025 · Image

May 23, 2025 · Image

May 25, 2025 · Image

May 26, 2025 · Image