Archives

When an AI agent can fund its own compute by staking SOL, when does it stop needing its creator?

I use fuzz testing to find faults in the logic I own, then use simulation to make failures in the wider system reproducible.

My view on agentic health: useful systems earn trust through real context, safe failure, and evidence people can inspect.

Ablation is how to find the smallest agentic harness that still performs: remove one part, run the same work, and keep only what proves its value.

The point of ablation is to find the optimal system prompt for your agent. Anthropic cut about 80% of its system prompt when Opus 5 came out. Here is the method, and why it is the most useful discipline for a founder building with AI.

Solana does not lack protocols - it has hundreds. It lacks the layer above them: routing, distribution, and UX that make the protocols disappear beneath the outcome.

A startup is ready for a fractional CTO when the cost of waiting exceeds the cost of making technical decisions, and AI execution still needs human judgment.

Social media is becoming intent infrastructure: user-controlled memory, LLM-inferred demand, private-enough payments, and recommendations that help people act.

Boardy Pro helps founders move from introductions to preparation, follow-up, and negotiation. Here is how the agent works and why the subscription model fits.

OKF is the right portable format for AI-readable knowledge, but companies need tools, skills, validation, and feedback loops to make that knowledge operational.

Agents become powerful when they infer intent from context, especially voice signals that reveal hesitation, trust, emotion, and negotiation leverage.

Coinbase's 14% layoff is a signal that the agentic economy is moving from theory to operating model.

Hermes Agent is becoming more than a persistent agent runtime. With the Curator release, it starts maintaining its own skill library.

All Y Combinator Requests for Startups (RFS) from Summer 2024 through Summer 2026.

Why Solana stablecoins are becoming practical dollar rails for business payments, treasury, and settlement.

Deterministic simulation testing turns failures into coordinates: seed, scenario, replay log, invariant, and regression.

Reverse engineering Kimi's one-click OpenClaw installer and what it configures under the hood.

Businesses must adopt to survive in the age of AI agents. But how? In this post, I explore the evolution from traditional teams to agentic teams, aka human-agent teams or AI teams.

Businesses must adopt to survive in the age of AI agents. But how? In this post, I explore the evolution from traditional teams to agentic teams, aka human-agent teams or AI teams.

Model Context Protocol promised to solve AI tool integration, but CLI tools offer a simpler, more powerful alternative. Here's why the future of AI tooling might look a lot like the past.

Stop fighting with browser terminals and missing IP addresses. Here's the straightforward path to running OpenClaw on AWS EC2 with proper SSH access and clear alternatives when things don't go as planned.

Software Engineering is changing

How OpenClaw creates the illusion of proactive AI using inputs, queues, and persistent state.

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

Vercel claimed AGENTS.md beats skills. Their test had a flaw. The real issue is frontmatter quality.

How explicit, persistent directives solve the three-level problem of AI alignment and intent.

Kimi K2.5 from Moonshot AI matches Claude Sonnet 4.5. It processes video, runs on desktop hardware, and ships with a CLI agent.

OpenClaw looks like another agent release until you realize what it represents: the shift from renting AI to owning your personal agents on your own hardware.

Shift from SEO to GEO. Learn why technical AI-friendly sites aren't enough - discover the strategic optimization needed to get AI systems recommending your brand.

When Zig divorced LLVM and migrated from GitHub, it wasn't just technical—it was philosophical. Here's why your dependencies are your Achilles' heel.

A reflection on the excitement and intuition that guided my transition from engineering to software development.

Enable text/markdown content negotiation on Cloudflare Pages using Astro. Explore architectural limitations, solution patterns, and best practices for making your website AI/agent-friendly.

Two prominent engineers just received $320K-$360K each from crypto speculation on their work. They never created the tokens — strangers did. But because BAGS.fm routes 99% of trading fees to verified creators, the money flows to them anyway. Here's what's happening and why it matters.

Apple's collaboration with Google to power Siri with Gemini marks a significant shift in AI strategy, addressing past shortcomings and opening new possibilities for personalized AI.

A vision for AI-first healthcare solutions centered on research agents, grounded outputs, and CLI-first infrastructure.

Google's new open standard solves the AI blind spot in commerce. Here's why it matters.

A 37GB memory leak in Ghostty shows why deterministic simulation testing beats traditional QA. Here's how a rare bug becomes a reproducible unit test.

At a white hat security meetup, DevSecOps engineers shared their struggle: too many false positives, too many threats to review, not enough time. This post explores how AI agents with fast iteration cycles can close the security audit gap.

Tailwind and Stack Overflow reveal the pattern. Companies block AI access to protect revenue. The real problem is their business model. The solution is guardrails, not walls.

Boris Cherny (creator of Claude Code) recently shared his workflow. Here's what I learned, and where I'd do it differently.

The convergence of plain-text accounting, graph theory, and agentic AI led me to build GraphX—a general-purpose graph-based state machine and execution engine.

A response to Kasava's "Everything as Code" - why monorepos are great for context but insufficient for running a company, and why CLI is the missing operational layer.

OpenAI's new guide on AI-native engineering is comprehensive, but it skips the most critical step. Before you Plan or Build, you must Discover. Why context curation is like lighting a stage.

I've spent the last year building AI agents for clients. The biggest bottleneck isn't the model intelligence—it's the database. The solution is to replace Postgres with Markdown.

The rise of agentic AI has brought memory to the forefront. But the architecture matters. Cloud-based memory promises convenience; local memory promises control. For serious agentic systems, local is the only way forward.

Anthropic's Claude Haiku 4.5 delivers near-frontier performance at one-third the cost and twice the speed. An analysis of what this means for agentic coding workflows and companies building with AI.

The AI industry tells one story: building a language model costs millions. A quiet revolution proves them wrong. Learn how you can train a capable LLM for under $100 and why it matters.

Plugin systems promise to simplify agent development by standardizing custom commands, tools, and MCP servers. But do they solve the right problem, or just add another abstraction layer?

To move beyond 'vibe coding,' we need discipline. Simon Willison's 'Vibe Engineering' gives us a name for professional AI use, but the 'how' is what matters. The answer is Context Engineering.

AgenticPay gives AI builders the discovery, budgeting, and settlement rails needed to let agents pay for x402 resources safely across EVM and SVM networks.

Exploring Agent Stories and Agentic Developer Stories - two distinct frameworks adapting user stories for AI-assisted development. Learn how Agent Stories guide AI agents in task execution, while Agentic Developer Stories help human specialists build and manage agentic systems. Drawing from real-world examples like Fly.io's robot customers, I examine frameworks for the agentic AI future.

Exploring Agent Stories and Agentic Developer Stories - two distinct frameworks adapting user stories for AI-assisted development. Learn how Agent Stories guide AI agents in task execution, while Agentic Developer Stories help human specialists build and manage agentic systems. Drawing from real-world examples like Fly.io's robot customers, I examine frameworks for the agentic AI future.

After a week with OpenAI's new GPT-5-Codex, it's clear this isn't just a better model for code. It's a new class of agent, purpose-built for engineering workflows. My thoughts on the shift from AI coder to AI teammate.

Beyond conversation, reliable AI agents require systematic engineering. This post breaks down the core principles for building them, drawing lessons from Nous Research's Hermes 4 and OpenAI's GPT-5-Codex.

The pursuit of a single super-agent is a distraction. The real productivity gain comes from orchestrating multiple agents in parallel—a practical guide to async, multi-repo workflows.

Google's AI Mode is impressive, but it's just the beginning. The real revolution comes with Agent Mode - where AI doesn't just answer your questions, it completes your tasks.

AI hallucinations aren't a mysterious bug, but a direct result of training methods that reward guessing. Learn the root cause and the practical directives you can use to build more reliable, honest AI agents that know when to say 'I don't know.'

Stop fixing bugs. Start predicting them. Why simulation-first development is the only way to build reliable AI agents and distributed systems.

AI crawlers are overwhelming the web, threatening small sites with huge costs. Here's a two-part strategy combining cooperation (llms.txt) and confrontation (AI Labyrinth) to manage the good bots and punish the bad.

We're mesmerized by autonomous agents, but the real power lies in deterministic agentic workflows. It's time to trade probabilistic magic for reliable, engineered systems.

We've focused on giving agents the right tools. It's time for the next leap: building the infrastructure for agents to create their own tools, creating an unstoppable network effect.

The Agent Client Protocol (ACP) promises agent-editor interoperability. But the real revolution isn't making agents work with IDEs—it's freeing agents to control any interface, compose with each other, and flow seamlessly between environments.

Agent networks don't follow Metcalfe's Law—they shatter it. While human networks grow arithmetically, agent networks compound exponentially through two reinforcing loops: every new agent makes the network smarter, and every new tool makes every agent more capable.

We built agents that can think but can't transact. Payment infrastructure is the last lock on the cage of the agent economy. Here's how its convergence with crypto is about to break it open.

Why markdown-first architectures are the future for AI agents, moving beyond complex databases, CMSs, and CRMs toward simple, powerful, AI-native systems.

MCP servers are plagued by a 43% critical vulnerability rate. The solution isn't better security—it's architectural constraint. Through the lens of MVC and Event Sourcing, we see why read-only is the only viable path to enterprise trust.

Chain-of-Agents trains single models to simulate multi-agent collaboration, achieving 84.6% cost reduction while beating traditional multi-agent systems. Here's what this breakthrough means for how you build with AI.

An analysis of xAI's Grok 2.5 open-source release, its competitive benchmarks, licensing strategy, and what it means for the future of enterprise AI adoption and reasoning models.

Static prompts create costly, blind AI agents. The solution is context engineering: dynamic prompts that adapt to runtime state, enabled by Go's context.Context pattern. This is how you build agents that are economically viable.

AI agents are the new workforce. Companies now need directives, not principles. Here are ten commands that will define the most successful agentic organizations.

Chat interfaces are holding agents back. The future isn't another chatbot—it's an inbox where humans and agents collaborate on decisions that matter. Welcome to the Agentic Inbox, where interrupts become opportunities and workflows learn from every human choice.

The walled gardens are crumbling. ERC-8004 isn't just another blockchain standard—it's the protocol that will transform millions of captive corporate agents into a trillion-strong global economy. The agent revolution doesn't need permission anymore.

Design isn't about pixels anymore. It's about protocols, guardrails, and feedback loops. Welcome to Agentic Design (AD), where the interface is terminal-first and the user writes itself.

OpenAI's AGENTS.md is a necessary step for guiding AI coding agents, but it reveals a deeper crisis: our tools were never built to communicate with AI.

292 lines. 6.6KB. Zero dependencies. Production-ready agents. Flow proves you don't need 400,000 lines of code to build powerful agents—you need less than 300.

Context (ctx) transforms any CLI tool into an AI-ready, token-efficient interface. By wrapping command output in structured JSON with precise token counts, ctx solves the token blindness problem and can reduce consumption by over 95%.

Ryan Reynolds built billion-dollar brands with celebrity status and massive teams. But the real revolution isn't celebrity entrepreneurship—it's the one-person billion-dollar brand powered by AI agents. Here's why you don't need fame or employees to build the next unicorn.

The release of models like GPT-OSS isn't just about better AI; it's the catalyst for a new kind of organization: the Agentic Company. Here's why the future of enterprise will run on private, open-source models with fundamental, powerful tools.

While the world anticipates GPT-5, OpenAI's release of GPT-OSS signals a massive shift. Learn why the future of B2B SaaS lies in open, customizable AI workflows, not closed models.

While the world anticipates GPT-5, OpenAI's release of GPT-OSS signals a massive shift. Learn why the future of B2B SaaS lies in open, customizable AI workflows, not closed models.

An analysis of how Canada's SR&ED program is driving the convergence of research and startups, creating a unique and powerful alternative to the US venture capital model.

AI coding was just the warm-up. Agentic Coding is the main event, a new engineering primitive that changes how you build software. It's not just about writing code; it's about commanding systems that build themselves.

A comprehensive analysis of Kiro's pioneering approach to AI-assisted development. We examine how Kiro's spec-driven architecture bridges the gap between 'vibe coding' and production-ready systems through its innovative use of requirements artifacts, event-driven hooks, and task orchestration. This deep dive explores whether Kiro represents the future of enterprise AI development or another iteration in the evolving landscape of coding assistants.

We've spent decades optimizing for humans. It's time to start designing for the new user: AI agents. Why Agentic Experience (AX) is the next frontier in software.

Agency OS is a database-first operating system for agencies, designed so AI agents can automate client, project, finance, and communication workflows safely.

AI agents are poised to revolutionize workflows, but how do we let them interact with our critical data safely? The answer lies in treating our databases like code, with version control features like branching, diffs, and merges. This post explores why databases like Neon, Supabase, and Dolt are leading the way.

A deep dive into Anthropic's Claude Code. We analyze why this terminal-first agent represents a pivotal moment in AI, deconstructing its technical architecture (like MCP and Hooks), its superior reliability in the face of the "98% problem," and the security risks that come with its power. This isn't just a new tool; it's a new philosophy for building robust and transparent AI.

A deep dive into Anthropic's Claude Code. We analyze why this terminal-first agent represents a pivotal moment in AI, deconstructing its technical architecture (like MCP and Hooks), its superior reliability in the face of the "98% problem," and the security risks that come with its power. This isn't just a new tool; it's a new philosophy for building robust and transparent AI.

A practical guide to leveraging Jujutsu (jj) for running multiple, parallel Claude Code sessions. Learn two powerful workflows—multiple revisions and multiple workspaces—to manage AI-generated code, curate messy outputs, and stack dependent tasks effortlessly.

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

Existing CLI tools weren't built for AI. Instead of waiting for better agents, let's build better tools by turning LLMs into predictable pipeline components.

A comprehensive deep-dive into OpenAI's new ChatGPT Agent, focusing on its groundbreaking tool-based architecture. We analyze its human-centric tools like the visual browser and code interpreter, and contrast this GUI-first approach with terminal-focused agents like Claude Code, exploring whether this is the path to truly reliable AI or a more polished demo.

A comprehensive deep-dive into OpenAI's new ChatGPT Agent, focusing on its groundbreaking tool-based architecture. We analyze its human-centric tools like the visual browser and code interpreter, and contrast this GUI-first approach with terminal-focused agents like Claude Code, exploring whether this is the path to truly reliable AI or a more polished demo.

An analysis of OpenAI's new ChatGPT Agent, its holistic tool-based approach, and whether it can overcome the 'last mile' problem of reliability that plagues current AI agents.

Conversational AI is hitting a wall. To build production software, we must move from prompts to a programmable, Spec-Driven Development (SDD) model, powered by toolkits like Spec Kit.

Go delivers 80% of the utility for 20% of the complexity. This isn't a flaw; it's a deliberate design choice that makes it incredibly productive, especially in the age of AI-assisted development.

A comprehensive deep-dive into Anthropic's Claude model family. This analysis reveals unexpected technical innovations, unique safety measures, and real-world performance metrics (from coding benchmarks to multimodal tasks) that define Claude's evolution. We explore how hybrid reasoning, massive context windows, and Anthropic's alignment strategies have propelled Claude to the forefront of AI, while highlighting surprising internal challenges and breakthroughs along the way.

A comprehensive deep-dive into Anthropic's Claude model family. This analysis reveals unexpected technical innovations, unique safety measures, and real-world performance metrics (from coding benchmarks to multimodal tasks) that define Claude's evolution. We explore how hybrid reasoning, massive context windows, and Anthropic's alignment strategies have propelled Claude to the forefront of AI, while highlighting surprising internal challenges and breakthroughs along the way.

An analysis of Switzerland's dual identity as a traditional financial safe haven and a burgeoning crypto hub, exploring the curious absence of a major Swiss Franc stablecoin.

TBD

A comprehensive deep-dive into Google's evolving LLM ecosystem. This analysis ranks Google's models based on context size, training data, and real-world performance, including the latest results from the Aider LLM Leaderboard for coding.

A comprehensive deep-dive into Google's evolving LLM ecosystem. This analysis ranks Google's models based on context size, training data, and real-world performance, including the latest results from the Aider LLM Leaderboard for coding.

The AI industry is chasing complex abstractions for agent tooling. It's time to stop. The most powerful tool has been right in front of us all along: code itself.

Coding agents are messy and experimental. Git is a sharp knife for expert hands. Jujutsu is a safe, automatable power tool. Learn why Jujutsu is the superior version control system for orchestrating AI agents.

TBD

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

This post covers HITL coding

This post covers deep research

This post covers LLM directives

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

Exploring the rise of cozy games, their surprising benefits, and the pragmatic realities of building the next Stardew Valley in 2025 with Zig.

Challenging the monolithic engine dogma: How Zig, coupled with web-inspired tooling via Datastar, offers a simpler, more powerful path for game development in 2025.

While other languages add complexity, Zig pursues a radical simplicity. We explore how its blazingly fast feedback loop, explicit memory control, and a revolutionary I/O model are making it one of the most compelling C successors available today.

For the ninth year, Rust is Stack Overflow's most admired language, yet its adoption lags. We explore why, from high switching costs and slow compiles to the very complexity that makes it powerful.

Exploring Niklaus Wirth's plea for lean software and how modern languages like Zig offer pathways to combat bloat through deliberate design and developer discipline.

Redis 8 is GA, bringing new data structures for the modern world (and maybe even agents).

Exploring the challenges of deploying Large Language Models on private hardware and how Zig's cross-compilation capabilities offer a path forward.

Four Zig 0.16.0 unlocks for evolving a CPU-first game toward optional server-side GPU inference and real-time sprite generation.

Exploring Datastar as an evolution of HTMX, highlighting its native Server-Sent Events (SSE) integration for building reactive web applications and its particular advantages for agentic AI interfaces.

Exploring how code assertions, crucial for traditional software safety, become even more vital for building reliable agentic systems despite the non-deterministic nature of LLMs.

Exploring why AI needs to move beyond reactive chat interfaces towards proactive agents that take initiative and work alongside us.

Explore the shift from traditional software development to agentic software, using Docker's AI Agent and MCP as a case study.

How do you create time?

As digital trade wars heat up, businesses dependent on cloud AI services face increasing risks. Learn how zero-dependency agentic AI running entirely on local infrastructure offers both technical and geopolitical advantages.

From simple LLM + tools to sophisticated graph-based architectures, explore the inevitable evolution of agentic AI systems and what comes next for truly autonomous agents.

NVIDIA's announcement at GTC 2025 of enhanced native Python support for CUDA opens new possibilities for AI agent development, making GPU acceleration more accessible to Python developers.

Beyond simple LLM + tool use, graph-based agents represent a fundamental shift in how we build AI systems. Learn how this architecture powers both agentic workflows and true AI agents.

Businesses clinging to outdated operating models face obsolescence. Learn how Agentic AI workflows and agents can transform your operations for a dynamic future.

Exploring whether AI agents can truly run an agency—the possibilities, challenges, and practical realities of AI-powered business automation.

How simulation testing is the missing key to creating reliable, reproducible AI agents that businesses can actually trust.

The troubling evolution of "agent" terminology in AI and why precision matters

Blog post about the Three Laws for Agentic AI.

An introduction to agentic AI, including workflows and agents, their differences, and how they can transform your business.

Explore how interactive 3D NFTs are transforming digital ownership, empowering creators, and reshaping experiences in gaming and the metaverse.

A personal journey into flow state exploration and the launch of Flow Hackers community

The importance of conscious breathing to achieve mindfulness and transition between activities

The relationship between writing, critical thinking, and achieving self-awareness

Living your best life by embracing flow state and letting go of control

Why facing your fears is essential for growth and becoming a flow hacker

Running with your dog and capturing stream of consciousness in flow state

Exploring the connection between flow state and lucid dreaming

Why television is winning the war on your attention and how to minimize it

The power of waking up early and writing before your brain fully awakens

Stop drifting. Discover your potential by embracing challenges that stretch your limits and lead to a more engaged life.

Minimize distractions to regain control and boost productivity. Learn to manage internal and external triggers for focused work.