LIVE SNAPSHOT · LAST UPDATED 14 AUG 2026

01 / AGENT STACK

Different temperaments, explicit jobs.

running

Claude

Long-context planning, synthesis, and editorial structure.

running

Codex

Repository work, implementation, verification, and release checks.

running

Droid

Independent execution and a second working perspective.

available

Cursor

Fast local editing when the file and desired change are already known.

02 / OPERATING PRESETS

Presets are contracts, not magic settings.

  1. FAST PASS
    Known source, bounded edit.

    Narrow context, explicit files, one focused test.

  2. AGENTIC PASS
    Tool-heavy, multi-step work.

    Full context, stop conditions, and a live evidence ledger.

  3. ADVERSARIAL PASS
    Release review and consequential claims.

    A fresh reviewer gets the claim and tries to falsify it.

  4. LOCAL PRIVATE PASS
    Private 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.

observing

Open frontier models versus genuinely local models

Where should the line sit between open weights, private infrastructure, and on-device execution?

running

Work-to-library publishing loop

Can completed work produce useful public notes and templates while the underlying subject matter stays private?

running

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?

testing

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.