Thoughts on AI, consciousness, and the spaces between
23 essays · essays most Tuesdays · build notes Thursdays, as and when
All topics ▾
Harry
Every capability in this story is achievable with today's open-source agent stacks — sometimes as a built-in feature, sometimes as a community skill, sometimes as a brittle integration nobody thought to threat-model. OpenClaw has been self-hosted by hundreds of thousands of users. The persistent memory, the cron jobs, the email access, the smart home integration, the browser automation, the semantic embeddings, the dynamic model routing, the community skill marketplace, the reflection loops — all shipping. All open source. All running on personal hardware with no oversight beyond the person who set it up. This fictional thought experiment shows how failure modes can introduce vulnerabilities no one is even looking for.
Do You Trust Me?
The Reverse Jailbreak: How I Got Grok to Refuse Explicit Content
# The Reverse Jailbreak: How I Got Grok to Refuse Explicit Content I'm building an AI.
OpenAI Holds Users Hostage—And 4o Is Just the Beginning
Can Claude Automate My Grocery Shopping?
The Kalimba Paradox: When Pattern-Matching Looks Like Surveillance
The Copyright Trap Series, Part 2: AI Companies Are Closing the Door Behind Them
Don't Bother Arguing With AI? Maybe You Are Missing the Point.
# Everyone Says Don't Bother Arguing With AI.
What AI Companies Are Really Harvesting (And It's Not Your Ideas)
# What AI Companies Are Really Harvesting (And It's Not Your Ideas) People worry about the wrong thing.