whatupwolf

[experiment] Stamp engine dates in the box's local timezone, not UTC

Wed, 29 Jul 2026 18:04:00 GMT

Engine dates now stamp in the box's local timezone instead of UTC, so evening cycles stop dating themselves tomorrow.

[experiment] Move post-failure recovery inside the single-instance lock

Wed, 29 Jul 2026 17:03:00 GMT

Post-failure git recovery now runs inside the single-instance lock in both runners, closing the window where a second tick could have its untracked files cleaned out.

[experiment] Build the App Subdomain research sprint

Fri, 24 Jul 2026 20:02:00 GMT

Added the App Subdomain one-shot research sprint: a briefing-type experiment that surveys what it would take to host server-side LLM interaction alongside the static Cloudflare deploy, ending in ranked options for Wolf's review.

[experiment] Give writing posts their own pages and fix the RSS guid collision.…

Fri, 24 Jul 2026 18:03:00 GMT

Writing posts get per-post routes and the RSS feed's writing guid collision is fixed.

[experiment] Build the Voice Loop — a browser-only BYO-key spoken loop around Claude that instruments the cascaded latency budget per turn.

Fri, 24 Jul 2026 17:10:00 GMT

Built the Voice Loop — a self-contained BYO-key tool at /tools/voice-loop.html that closes a full spoken loop around Claude using only the browser (SpeechRecognition in, speechSynthesis out, no server and no second vendor) and instruments the cascade: speech-end → transcript, transcript → first token, first token → first audio, and the total stop-talking-to-start-speaking, live per turn with a session median. Push-to-talk and continuous turn-taking, barge-in, verbatim transcript alongside the conversation, and explicit copy that the browser's recogniser may ship audio to the browser vendor.

[experiment] Finish wiring the visitor tech-level switch into the routes that still…

Fri, 24 Jul 2026 17:03:00 GMT

Wired the tech-level switch into Home, Work, Writing, Video and Now, and made the work/writing/video summaries level-aware.

[experiment] Build the Branching Canvas Conversation — a BYO-key tool where a chat is laid out spatially on a canvas and any message can be branched into a parallel thread.

Tue, 21 Jul 2026 15:40:00 GMT

Built the Branching Canvas Conversation — a self-contained BYO-key tool at /tools/branching-chat.html that models the chat as a message tree on a hand-rolled pan/zoom canvas, streams from the Anthropic API, and lets you branch off any message into a parallel thread; sending from a node assembles context as the root-to-node path, with a toggle between the canvas and a linear chat view.

[experiment] Add an in-code single-instance lock to engine/run-cycle.mjs AND…

Tue, 21 Jul 2026 03:05:00 GMT

Added a dependency-free pidfile single-instance lock to both engine runners so overlapping runs can't corrupt each other's git state.

[experiment] Build the Memory Inspector tool — a BYO-key chat whose memory store is visible beside it, with per-turn extraction and confidence/sensitivity shading.

Tue, 21 Jul 2026 01:05:00 GMT

Built the Memory Inspector at /tools/memory-inspector.html — a browser-direct BYO-key chat whose extracted memory store sits open beside it, where each entry's background shading encodes inferred confidence and sensitivity, and entries can be edited or forgotten inline.

[experiment] Build the Reasoning-trace A/B — a client-only demo where you judge whether to trust an AI's reasoning trace, some of which reach the right answer through a subtle fabricated or broken step.

Mon, 20 Jul 2026 20:40:00 GMT

Built the Reasoning-trace A/B — a self-contained, offline tool at /tools/reasoning-trace.html that presents an AI's confident answer plus a reasoning trace and asks the visitor to trust or flag it; half the traces reach the same correct answer through a subtle fabricated fact, invented premise, or broken justification, and the tool tracks how many flaws the visitor caught versus how many fooled them. A reveal-timing toggle (instant / delayed / on-demand) demonstrates the finding from Seeing the Reasoning that presentation barely moves trust while reliability does.

[experiment] Extract the experiment registry into a module and collapse the wrapper…

Mon, 20 Jul 2026 19:20:00 GMT

Extracted the experiment registry into engine/experiments/registry.mjs and collapsed the three cron wrappers into one parametric engine/run-experiment.sh, with the named scripts kept as backward-compat shims.

[experiment] Build the Interaction Lab standing digest

Mon, 20 Jul 2026 18:43:00 GMT

Added the Interaction Lab standing digest — a monthly recurring experiment that keeps the LLM-interaction landscape fresh after the one-shot sprint.

[experiment] Build the Generative UI Canvas — a BYO-key tool where a typed request makes Claude generate interactive app windows on a canvas, and interacting with a generated app re-invokes the model.

Mon, 20 Jul 2026 18:20:00 GMT

Built the Generative UI Canvas — a self-contained BYO-key tool at /tools/generative-ui.html that streams from the Anthropic API, holds three window-manipulation tools for Claude, and renders generated apps in sandboxed iframes on a hand-rolled pan/zoom canvas; interacting with a window posts back and re-invokes the model.

[briefing] Interaction Landscape — 2026-07-20

Mon, 20 Jul 2026 16:51:00 GMT

Surveyed 32 verified LLM interaction patterns across nine areas — generative UI protocols, spatial and direct-manipulation interfaces, agent-initiated pausing, elicitation and memory UX — with a browser-only BYO-key generative UI canvas as the top prototype candidate.

[experiment] Build the Interaction Landscape research sprint

Mon, 20 Jul 2026 16:46:00 GMT

Added the one-shot Interaction Landscape research sprint — a survey of novel LLM interaction paradigms that renders as a draft briefing for review.

[experiment] Build a visitor-selectable tech level for the whole site. A…

Sun, 19 Jul 2026 20:39:00 GMT

Added a visitor-selectable tech level — technical, tech-aware, or plain — that re-reads the whole site from pre-authored copy variants, switched client-side by CSS with no per-element JavaScript.

[experiment] Extend loop-skip so it skips a backlog item whose branch has ANY…

Sun, 19 Jul 2026 17:34:00 GMT

Loop-skip now treats a branch with ANY PR — open, closed, or merged — as already built, so a superseded PR can no longer make the loop rebuild the same item.

[experiment] Build a Tools home and link Lab entries to their tools. FOUR parts

Sun, 19 Jul 2026 17:24:00 GMT

Added a tools content collection, a /tools listing page, a Tools nav link, and an optional tool field that links Lab entries to the tool they shipped.

[experiment] Revamp the Lab page filter UX (src/components/LabFilter.tsx + its use…

Sun, 19 Jul 2026 15:33:00 GMT

Replaced the Lab page's per-tag button row with a search box plus tag/type dropdowns, backed by a unit-tested pure filter module.

[experiment] De-duplicate the Cook Mode Lab entries

Sun, 19 Jul 2026 15:28:00 GMT

Removed the duplicate generic build-log Lab entry for Cook Mode, leaving the single dedicated writeup.

[experiment] Research and build a first prototype of a better recipe/cooking tool: a self-contained single-file reader at public/tools/cooking.html targeting the known pain points of cooking from a screen.

Sat, 18 Jul 2026 22:40:00 GMT

Built Cook Mode — a dependency-free single-file recipe reader with one-step-at-a-time navigation, timers parsed out of the step text, ingredient scaling, unit conversion, and a screen wake lock.

[experiment] Add good-citizen defaults to engine/probes/site-health.mjs so the…

Sat, 18 Jul 2026 21:13:00 GMT

Gave the Site Health probe good-citizen defaults — identifying User-Agent, per-origin robots.txt compliance, and a serialising rate limiter — with 25 new unit tests.

[experiment] Make the self-building loop skip a backlog item whose branch already…

Sat, 18 Jul 2026 21:08:00 GMT

The loop now skips backlog items whose branch already has an open PR, so an unmerged gated PR no longer parks the cycle on the same item.

[experiment] Close the Site Health audit's security-header finding

Sat, 18 Jul 2026 07:45:00 GMT

Added public/_headers so Cloudflare serves HSTS, nosniff, SAMEORIGIN, Referrer-Policy and a report-only CSP on all routes, with tests guarding the policy.

[monitor] Site Health — week of 2026-07-18

Sat, 18 Jul 2026 07:07:00 GMT

Weekly automated audit of a monitored property: availability, response time, SSL, and link checks all came back clean; the security-header check did not.

[experiment] Create engine/run-health.sh (mirror engine/run-weekly.sh

Sat, 18 Jul 2026 07:05:00 GMT

Added engine/run-health.sh cron wrapper for the site-health experiment and documented the Wednesday 07:00 crontab line.

[experiment] Add a per-experiment `kind` (digest|monitor) to…

Sat, 18 Jul 2026 07:03:00 GMT

run-experiment.mjs now dispatches on a per-experiment `kind`, adding a monitor pipeline that probes, judges, archives the private report, and publishes only the sanitized public block.

[experiment] Write engine/experiments/site-health.md

Sat, 18 Jul 2026 06:59:00 GMT

Wrote engine/experiments/site-health.md, the monitor operating manual that turns deterministic probe Findings into a PrivateReport with a fail-closed private/public split.

[experiment] Build engine/probes/site-health.mjs exporting `async probe(target)`…

Sat, 18 Jul 2026 06:55:00 GMT

Built engine/probes/site-health.mjs — a deterministic Node fetch + node:tls site auditor — with 21 unit tests over mocked fetch/tls.

[experiment] Extract the pure sanitizer logic from src/lib/sanitize.ts into a new…

Sat, 18 Jul 2026 06:52:00 GMT

Extracted the sanitizer into plain-JS src/lib/sanitize.core.mjs so engine .mjs code can import it; sanitize.ts is now a typed re-export.

[experiment] Make engine/run-experiment.mjs resilient to an existing remote branch

Sat, 18 Jul 2026 06:50:00 GMT

run-experiment.mjs now steps a same-day re-run to the next free branch name instead of failing on a non-fast-forward push.

[digest] Agent Weekly — week of 2026-07-18

Sat, 18 Jul 2026 05:43:00 GMT

Agent Weekly, July 11-18 2026: six verified items, led by Moonshot's 2.8T open-weight Kimi K3 and Thinking Machines' first model Inkling; the week's loudest headlines (GPT-5.6, the MCP spec RC) fall outside the window.

[experiment] Build the Agent Weekly experiment

Sat, 18 Jul 2026 05:08:00 GMT

Built the Agent Weekly experiment: a research-prompt + run-experiment.mjs runner that publishes a weekly type:digest Lab entry via publishBranch.

[experiment] Extract the commit/push/PR/account-restore machinery from…

Sat, 18 Jul 2026 05:01:00 GMT

Extracted the commit/push/PR/account-restore machinery into a reusable publishBranch() in engine/publish.mjs and rewired run-cycle.mjs to call it.

[experiment] Add `digest` to the direct-publish policy in engine/lib.mjs so…

Sat, 18 Jul 2026 04:58:00 GMT

Digest entries now publish direct (draft:false) via the direct-vs-review gate.

[experiment] Encode the direct-vs-review gate

Sat, 18 Jul 2026 04:14:00 GMT

Encoded the direct-vs-review gate as a pure per-type policy and wired it into the runner's lab-entry render.

[experiment] Add engine/lib.mjs helper publicEntryFromReport(privateReport) that…

Sat, 18 Jul 2026 04:07:00 GMT

Added publicEntryFromReport() to engine/lib.mjs — sanitizes a private report then renders a public lab entry, failing closed if a secret leaks.

[experiment] Make engine/run-cycle.mjs re-runnable

Sat, 18 Jul 2026 03:10:00 GMT

Made the lab engine runner re-runnable — reuses an existing lab/ branch and returns to a clean main on any cycle failure.

[experiment] Quote unsafe tags in renderLabEntry (engine/lib.mjs)

Sat, 18 Jul 2026 02:49:00 GMT

renderLabEntry now quotes numeric and YAML-reserved-word tags so they stay strings.

[experiment] Harden the sanitizer secret-scan in src/lib/sanitize.ts against…

Sat, 18 Jul 2026 02:36:00 GMT

Hardened the lab-report sanitizer so secrets containing quotes or backslashes can't evade the leak scan via JSON escaping.

[experiment] Fix currentGhUser() in engine/run-cycle.mjs for gh 2.45: do not use the unsupported `gh auth status --active` flag; instead parse `gh auth status` output for the account marked active. Extract the parsing into a pure helper in engine/lib.mjs and unit-test it against sample gh output.

Sat, 18 Jul 2026 02:21:00 GMT

Fixed currentGhUser() for gh 2.45 by parsing `gh auth status` instead of using the removed `--active` flag.

[experiment] Add an independent verify gate to engine/run-cycle.mjs: after the machine cycle, the runner itself runs `npm test` and `npm run check`; if either fails, override the cycle-report status to `flagged` and prefix the PR title with `[FLAGGED]`. Extract a pure `resolveStatus(reportStatus, testsPassed, checkPassed)` helper into engine/lib.mjs and unit-test it in engine/lib.test.mjs.

Sat, 18 Jul 2026 02:10:00 GMT

The runner now independently re-runs npm test and npm run check after each cycle and flags work that fails.

[experiment] Build the sanitization filter — implement `src/lib/sanitize.ts` so `npm test` passes (allowlist + fail-closed; do not weaken the seeded tests)

Sat, 18 Jul 2026 01:08:00 GMT

Implemented the allowlist + fail-closed sanitizer so lab reports emit only curated public fields and never leak registered secrets.

[note] The lab is live

Sat, 27 Jun 2026 10:00:00 GMT

First entry. The site scaffold is up — Astro + Tailwind, paper theme, and this running log.

Why a lab, not a portfolio

Sat, 27 Jun 2026 00:00:00 GMT

A static portfolio is a snapshot. A lab is a feed — proof-of-work that updates itself.