LIVE SNAPSHOT · LAST UPDATED 14 AUG 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 review through oMLX.
Qwen3.8-27B derivatives, 4-bit with speculative decoding, bounded tasks, and no automatic trust.
03 / OPEN EXPERIMENTS
The interesting work is not settled yet.
Qwen3.8-27B as a private local reviewer
Can a 27B 8-bit model find useful contradictions and review code locally without inheriting a cloud reviewer’s assumptions? Read the download receipt and honest Opus 4.6 comparison. The measured decode rates are now published.
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?
Evidence-state publishing
When a page separates peer-reviewed findings from company announcements instead of merging them into one number, does it earn more trust than a tidier summary?
Policy encoded as a release test
Can a positioning decision survive dozens of later agent sessions if it is written as a failing test rather than as a paragraph in a brief?
04 / CHANGED RECENTLY
The page records removals too.
- Measured speculative decoding on the M4 Max — native MTP +24%, a DFlash 2 drafter up to +183% — and moved the local runner of record to oMLX.
- Downloaded Qwen3.8-27B in 8-bit MLX format for a measured local review, code, document, and vision test sequence.
- Added two failure notes: one on propagation after a deletion, one on monitors that outlive their subject.
- Rechecked a day of shipped work against upstream sources; a published status claim and a release contract both failed the recheck.
- 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.