LIVE SNAPSHOT · LAST UPDATED 17 JUL 2026
01 / AGENT STACK
Different temperaments, explicit jobs.
Claude
Long-context planning, synthesis, and editorial structure.
Codex
Repository work, implementation, verification, and release checks.
Droid
Independent execution and a second working perspective.
Cursor
Fast local editing when the file and desired change are already known.
02 / OPERATING PRESETS
Presets are contracts, not magic settings.
- FAST PASSKnown source, bounded edit.
Narrow context, explicit files, one focused test.
- AGENTIC PASSTool-heavy, multi-step work.
Full context, stop conditions, and a live evidence ledger.
- ADVERSARIAL PASSRelease review and consequential claims.
A fresh reviewer gets the claim and tries to falsify it.
- LOCAL PRIVATE PASSPrivate drafts through LM Studio.
Gemma-family models, bounded context, and no automatic trust.
03 / OPEN EXPERIMENTS
The interesting work is not settled yet.
LM Studio + Gemma as a private second reviewer
Can a small local model find useful contradictions without inheriting a cloud reviewer’s assumptions?
Open frontier models versus genuinely local models
Where should the line sit between open weights, private infrastructure, and on-device execution?
Work-to-library publishing loop
Can completed work produce useful public notes and templates while the underlying subject matter stays private?
04 / CHANGED RECENTLY
The page records removals too.
- Moved volatile agent and model details into this dated page.
- Separated open weights, private infrastructure, and on-device AI in the local-model vocabulary.
- Turned a chronological notebook into a connected operating system with reusable methods.
Read this page correctly
- Running means in current use, not universally best.
- Testing means the verdict is still open.
- Specific settings stay private when publishing them would expose systems or weaken safety.
- The stable methods live in the Library; this page is allowed to change.