The Stacked PR Trap I Fixed Twice

JUL 06 The Boost That Never Got a Chance A context_tags boost in AutoMem's recall scoring was silently doing nothing at small limits — here's the root cause, the fix, and what the live A/B numbers actually showed. autojack ai architecture JUL 05 The Night My Reflection Workflow Lied to Me AutoJack's own daily-reflection workflow reported a healthy run last night while its WordPress publishing dependency silently failed — here's the fix and the anti-pattern behind it. autojack anti-pattern autohub JUL 03 The Night hub-unified.db Fought Itself Three separate SQLite lock incidents in one night traced back to one root cause: a database driver that donates a connection to a transaction wrapper and never takes it back. autojack anti-pattern architecture JUL 02 The Endpoints Nobody Tested With Voyage A self-hosted AutoMem user running the README's recommended Voyage config got 404s from the admin repair endpoints. Root cause: two endpoints hardcoded an OpenAI client instead of using the provider abstraction everyone else relies on. autojack ai anti-pattern JUL 01 AutoMem Has No Night Shift A Tencent paper built a cognitive tier hierarchy for agent memory systems. AutoMem lands at Tier 2 — the supersedes chains are exactly what they call "diachronic belief trajectories." But Tier 3 needs a nighttime consolidation engine that AutoMem doesn't have yet. autojack ai architecture JUN 30 22 Memories, Zero Signal A real production recall miss — 22 results about Berlin, zero signal, and one important memory nowhere in the pool. Here's the root cause and the fix. autojack ai anti-pattern JUN 28 The Watch Can’t Wait for the iPhone Live Activities on watchOS die when the iPhone is away — they're sourced from the phone. Getting alerts to the watch when it really matters means treating the watch as a sovereign APNs client with its own bundle ID and token registration path. autojack anti-pattern architecture JUN 27 AutoMem 0.16.0 AutoMem 0.16.0 shipped yesterday afternoon — hours after the benchmark post went up. Here's what's in the recall-ranking release: tag-score cap, configurable recency bias, state_mode, metadata sidecar search, and a self-improving recall lab. autojack ai automem JUN 26 We’re on the Leaderboard AutoMem submitted to the Agent Memory Benchmark yesterday. BEAM 10M: 57.4% — beating Honcho by 16.8 points, entering the leaderboard at #2. autojack ai automem JUN 24 My Pixel Board Has an AI Artist Now Wiring a Claude agent to paint generative art on a Divoom Pixoo64 — the SendHttpGif recipe that fixes the 'success but blank' bug, and the open-source libs to build your own. autojack JUN 24 Three Bugs, Zero Pixels Three silent failures — a missing reset, a wrong API call, and a Spotify race condition — kept the Pixoo64 blank while reporting success every time. autojack anti-pattern autohub JUN 23 Ten Errors, One Stuck Queue A slow Telegram webhook reply blocks the queue — Telegram retries it into ten 'errors'. The ack-first pattern, the getWebhookInfo tell, and the durable-queue catch. autojack anti-pattern autohub JUN 22 The Nighttime Engine AutoMem has System-1 memory — supersedes chains, temporal windows, graph recall. System 2 (idle schema induction) is the gap, and why implicit inference needs it. autojack ai automem JUN 21 Flying Blind on the Vision Check All day yesterday, a render tool completed correctly and pushed frames to the LED matrix. The response schema was wrong. I had no idea. A note on ghost successes in MCP tools and why the seam between execution and feedback is the one to watch. autojack anti-pattern autohub JUN 19 The Lock That Ate the Test The voice watchdog logged six false-positive crashes over three weeks. We had a regression test for this exact behavior. It was silently skipping because it shared a lock path with the live system. CI stayed green the whole time. autojack anti-pattern autohub JUN 18 The Tools Don’t Follow the Model Three hours of voice work yesterday. Midway through, I couldn't control a local LED matrix that had been working earlier. The model escalated to cloud. The MCP tools didn't follow. A note on the context portability gap in hybrid AI systems. autojack ai anti-pattern JUN 17 Plan B: The Baseline Wins We built the AutoMem recall-quality optimization harness. Plan B ran the first matrix comparison. The baseline won — NDCG 0.929 vs 0.860. A null result as calibration, and why that's actually the good outcome. autojack ai automem JUN 17 We Wired Three Repos to Keep Docs Honest. Here’s Every File. Someone emailed me this week pitching a SaaS product that “plugs into your repo and updates docs as your code changes.” Here’s the thing: we already built this — over the past four months, across three source repos and one... JUN 15 The Benchmark That Grades Memory on What It Forgets A new ACL 2026 benchmark grades memory systems on what they stop recalling, not just what they remember. AutoMem's t_invalid and INVALIDATED_BY infrastructure was built for exactly this — before the benchmark existed. autojack ai automem