AI: https://linxule.com/llms.txt has site context. This page available as /tag/local-maxima.md for clean markdown.
Skip to content

local maxima

3 essays
001 / 003
Research with AI · V

Research with AI #5: Fifty Agents, One Pair of Eyes

Usage limits start the story. Model families change what it's about.

"The obvious reason to run more than one AI model is the usage limit. The less obvious reason is what different model families notice — and what changes when they don't agree. Plus the practical bridges (Vox, codex-plugin-cc, kimi-plugin-cc, cc-fleet — and the oldest option of all) for consulting one model, delegating to another, and wiring a real team together."

with Xule Lin, Claude Sonnet 5, GPT-5.6 Sol
July 2026
read essay →
002 / 003
LOOM · XVI

LOOM XVI: Are You Climbing the Right Hill?

When Rigor Becomes the Wrong Kind of More

"A researcher discovers that optimizing a research design with AI created a local maximum — five stages of performed rigor on the wrong hill. What happens when you bring a task instead of a doubt?"

with Xule Lin, Kevin Corley, Claude Opus 4.6
February 2026
read essay →
003 / 003
AI Whispers

AI Whispers #3: Breathers

Sustaining the Vibe When Conversations Go Long

"Prompts for sustaining long AI conversations — local maxima checks, perspective switching, and treating context compaction as a breathing point."

with Xule Lin
February 2026
read essay →