Elroy

I'm working on an iPhone app called Tack.

I recently wrote about optimizing repos for AI, but I've not quite settled on the question of, **should you optimize repos fo...

A colleague recently complained to me about the hassle of organizing information in AGENTS.md / CLAUDE.md.

AI is a Floor Raiser, not a Ceiling Raiser Also published at tombedor.dev/ai-is-a-floor-raiser A resha...

Add Autonomy Last A core challenge of using LLM's to build reliable automation is calibrating how much autonomy to give to models.

Yes or No, Please: Building Reliable Tests for Unreliable LLMs For LLM-based applications to be truly useful, they need predictability: While the free...