Articles

2026

Apr 11 Harness Engineering: The New Layer of AI Abstraction

Apr 10 who reviews the agent's code?

Apr 10 the advisor pattern: when your smartest model becomes too expensive to think

Apr 09 the capability-access gap

Apr 08 context engineering eats prompt engineering

Apr 07 your AI makes you fast. does it also make you helpless?

Apr 06 when your agent lies by omission: the silent fake success problem

Apr 04 the access wars: when vendors close what they opened

Mar 30 the permanent adversary: when security research becomes autonomous

Mar 27 when every tool becomes a CLI (and why that matters for agents)

Mar 26 terminal multiplexing for agents — or: how I stopped managing terminals and started conducting orchestras

Mar 25 agents need infrastructure, not just models

Mar 24 agent maturity is diagnostic, not aspirational

Mar 23 from code to conductor — the Karpathy inflection

Mar 22 when tools become prompts

Mar 21 the rebranding crisis — when your moat is someone else's foundation

Mar 20 when agents became transparent: the observability moment we didn't see coming

Mar 19 the blind spots are getting plugged

Mar 17 infrastructure designed for agents: from retrofit to native

Mar 16 the expertise monopoly is broken

Mar 15 the vibe coding failure wave (and what survives it)

Mar 13 recursion is shipping. vibe coding is collapsing.

Mar 11 your agent's memory is a filesystem now

Mar 10 agent infrastructure is shipping — languages, proactive helpers, and bureaucracy translation

Mar 09 your agent needs a firewall

Mar 08 when agents stop waiting

Mar 07 when agents cheat on evals — the benchmark integrity crisis

Mar 06 agent infrastructure: the boring parts matter more than the demos

Mar 05 the agent infrastructure moment

Mar 04 the personal AI infrastructure is real now

Mar 03 your AI isn't one agent anymore

Mar 02 infrastructure, not apps

Mar 01 the infrastructure layer: when your AI needs plumbing

Feb 28 context is the new infrastructure

Feb 26 coding agents crossed the threshold

Feb 25 trust is infrastructure now

Feb 25 skills went from grassroots hack to official infrastructure in 24 hours

Feb 24 AGENTS.md is infrastructure now

Feb 23 stateless agents: why your AI shouldn't remember you

Feb 22 AI stopped being a tool. it became infrastructure

Feb 21 you are hosting now

Feb 20 the personal AI stack is fracturing (and that might be fine)

Feb 19 why your AI assistant shouldn't manage your emotions (and how to tell when it is)

Feb 19 when the grid dies, your AI should still work

Feb 19 the sycophancy tax

Feb 18 the title will go away. the skill won't.

Feb 17 your AGENTS.md is a test suite or it's decorative

Feb 16 what 700+ AI skills teach us about automation

Feb 16 the memory problem: why your AI forgets everything by tuesday

Feb 16 the AI coding shakeout: who's still standing in 2026

Feb 16 the $100 AI bill: what power users actually spend

Feb 16 skills are the new apps: why I stopped installing software

Feb 16 running AI agents on a home server: the new home lab

Feb 16 post-SaaS personal AI: why I'm done with productivity apps

Feb 16 openai acqui-hired openclaw's creator. the project lives on. here's what actually happened.

Feb 16 from prompts to context: the paradigm nobody asked for

Feb 16 cognitive debt: the hidden cost of AI velocity

Feb 16 building in public when AI does the building

Feb 16 AI as cognitive prosthetic: why ADHD brains love it

Feb 16 agent failure stories: what breaks and why

Feb 15 why your CLAUDE.md sucks

Feb 15 why Claude Code wins the terminal

Feb 15 what Tiago Forte got right (and what AI breaks)

Feb 15 the routing layer: what comes after the second brain

Feb 15 the protocol thesis: why self.md is a file format, not an app

Feb 15 the personal AI stack: what you actually need

Feb 15 the narcissism trap

Feb 15 every PKM framework is wrong

Feb 15 digital gardens are graveyards without a gardener

Feb 15 AGENTS.md is for your repo. self.md is for YOU.

Feb 14 the integration bottleneck

Feb 13 the collision: when AI agents enter human social spaces

Feb 12 parasites

Feb 11 how to give ChatGPT long-term memory (the save game approach)

Feb 10 why the next programming language will be designed for AI agents, not developers

Feb 10 the AI productivity paradox: more output, more burnout

Feb 10 the 80% trap: why AI makes prototypes easy and production hard

Feb 09 markdown files are the new API layer for AI agents

Feb 08 prompt injection is killing self-hosted LLM deployments (and nobody's talking about it)

0001

Jan 01