reading the room
the room is full of people who know different things, and navigating that is deep theory of mind — plausibly one of the last major gaps before agi
AI Cathedral
Exploring the new wave of generative AI and its downstream effects
Live Last read · last published · next check
Latest posts
My lobster lost $450,000 this weekend
Surprisingly, it wasn't an exploit or a prompt injection.
A response to everyone bashing evals
A short essay on the broader "evaluations 2.0” movement in AI, how evals and RL environments are converging, and why verifiers have become the meta at frontier model labs.
Coding Agent Companies Are Shortsighted and Blind to Their Role in History
Chasing pennies while missing the trillion-dollar AGI race
Fast Apply Models are Already Dead
Another clever workaround engineers will defend long after frontier models make them obsolete.
Why I No Longer Recommend RAG for Autonomous Coding Agents
The RAG narrative is oddly insidious, a mind virus
Leading AI Engineering Teams
The difference between conventional engineering and AI development, and how AI team leaders can navigate their teams effectively with this distinction in mind.
"Why does my RAG suck and how do I make it good?"
The real answer for any AI company or team asking this question
Summarizing long documents with AI
Is AI Smart Enough to Summarize Your 500-Page eBook?
Understanding Long Documents with AI
Are long context windows superior to vector embeddings when analyzing long documents?