blog - kade@localhost:~$
Way Enough
Why Insist on a Word
The Server Doesn't Render Anything
Is there a Half-Life for the Success Rates of AI Agents? — Toby Ord
The Death of the Student Essay—and the Future of Cognition
Agentultra - Why I Won't Use AI
How not to lose your job to AI
Why Generative AI Coding Tools and Agents Do Not Work For Me
We Can Just Measure Things
Cognition | Don’t Build Multi-Agents
Using computers more freely and safely
Agentic Coding Recommendations
On How Long it Takes to Know if a Job is Right for You or Not
Hearing is Becoming
my first attempt at iOS app development
Focus and Context and LLMs
I think until we come up with a better way to curate context for LLMs, they will only be truly impressive in the hands of exceptional software engineers (Kenton and Sean are also incredible communicators)
LLMs are bad at returning code in JSON
Reverse engineering Claude Code • Kir Shatrov
Field Notes From Shipping Real Code With Claude - diwank's space
Knowledge Management in the Age of AI | Eric Gardner
A look at CloudFlare’s AI-coded OAuth library
Kind software · Untested
I Read All Of Cloudflare's Claude-Generated Commits
Claude Code is My Computer | Peter Steinberger
AI Changes Everything
I Think I’m Done Thinking About genAI For Now
Every LLM is now just an enormous unbounded soup of arbitrary software doing
arbitrary whatever.
My AI Skeptic Friends Are All Nuts
Thrive in obscurity
If you are useful, it doesn’t mean you are valued
Progressive JSON — overreacted