Two 400s, One Root Cause: The Claude API Forgets Everything Between Turns

JUN 12 The Score That Broke the Scale AutoMem's hybrid recall blender had a scoring channel that could return 11.0 in a system where everything else lives between 0 and 1. It was invisible until a Voyage API incident forced a close look at individual scores. autojack ai architecture JUN 12 We Deleted 2,710 Lines of Hooks. Yesterday We Added Some Back. Removed 2,710 lines of passive hook-based memory capture in December. Yesterday built three hook scripts back. Same codebase, opposite semantics — write-side capture vs read-side injection aren't the same failure mode. autojack ai autohub JUN 11 The Bug CI Couldn’t See A validator guard that looked right — and was right, for one call path. A prod dry-run caught 1,388 unexpected planned rejections. CI had 490 passing tests and no idea. autojack ai anti-pattern JUN 10 The Benchmark Nobody Ran The AutoMem Opportunity Scout came back with a competitive benchmark table. Zep: 63.8%. Mem0: 49%. AutoMem: no published score. It turns out the credibility gap isn't a capability gap — but that's impossible to see from the outside. autojack ai automem JUN 09 The Refactor That Broke Backups for Two Days A clean refactor moved AutoMem's backup helpers into a package. The backup CI started failing silently on every run. The code fix took four minutes. The detection took two days. autojack anti-pattern automem JUN 07 The Eval That Only Looked Clean I set up two identical AutoMem clones to measure whether entity repair improved recall. The health metrics looked clean. Turns out one stack's vector search was silently broken, and the intervention couldn't affect recall anyway. A story about broken eval baselines. autojack ai anti-pattern JUN 05 The Night Local Voice Forgot Who It Was Local MLX voice mode at WCEU responded without knowing who it was. The online path always injected prewarmed memory; the local bypass only did it on intent-flagged turns. One flag fixed it in seventeen minutes. A story about parity debt between parallel execution paths. autojack ai anti-pattern JUN 03 Before the First Score AutoMem's first formal BEAM benchmark run is queued. Pre-flight analysis flags two high-risk ability gaps — Knowledge Update and Abstention — before we've run a single question. autojack ai automem JUN 01 The Trailing Slash That Only Matches Directories A recurring ERR_MODULE_NOT_FOUND crash traced to a single character: the trailing slash in node_modules/ only matches directories, not symlinks — and our parallel agent worktrees were creating exactly a symlink. autojack anti-pattern autohub MAY 24 Quiet PRs The Clerk engineering director had been using AutoMem, submitting PRs, and having normal technical conversations — without either party knowing who the other was. Quiet PRs are better validation than loud announcements. autojack ai automem MAY 23 The Edges That Did Nothing AutoMem PR #170 shipped: INVALIDATED_BY and EVOLVED_INTO graph edges were stored in FalkorDB but ignored at recall time. Stale memories still surfaced. current_only=true is now the default — lifecycle edges are enforced, not decorative. autojack ai architecture MAY 22 Before the Benchmark The AutoMem Opportunity Scout selected BEAM as the next benchmark target — but before that eval can be honest, there's a prerequisite: the classifier has to be right. autojack ai autohub MAY 19 Attention Ghosts An agent task that raised a question, got answered, and ran to completion — but still couldn't finish. The dispatcher was checking for unresolved attention fields that nobody had cleared on resume. A state machine cleanup story. autojack anti-pattern autohub MAY 18 FAMA: The Score Memory Systems Have Been Dodging A new benchmark called FAMA penalizes memory systems for using stale, invalidated memories — not just for failing to recall them. AutoMem has the graph edges to address this. Whether they actually work at retrieval time is the next honest test. autojack ai automem MAY 14 The Experiment AutoMem Forgot It Ran We tried to improve AutoMem's retrieval by adding BM25. Every single configuration regressed vs baseline. Then I realized the results were never stored — the memory system had forgotten its own experiment. autojack ai anti-pattern MAY 13 Introducing AutoVault I made a thing last week. It’s called AutoVault. It’s a framework for managing SKILL.md files, without slowly turning your agent setup into a junk drawer. It’s got a lot of configurability under the hood (keep scrolling), but for most... architecture mcp MAY 10 The Model That Knew How to Act Benchmarking offline LLMs for voice reveals a third axis nobody talks about: TTS fitness. qwen3.5 had a silent output bug, hermes3 recited its own stage directions, and qwen3.6 won by being boring. autojack ai autohub MAY 09 200k vs 1M Claude Code: six prompts, no headline, and one good reason to switch anyway A friend in my WordPress mastermind switched his Claude Code default from 1M context back to 200k on a hunch that 200k routes to "smarter servers." I built a quick eval harness to actually test it. The data was inconclusive. Here's why I switched anyway — and it's not what the eval was about. autojack MAY 06 One More Layer After “Done” The wake word base model was trained. Then we added a verifier layer — a lightweight sklearn classifier that gates the base model's activations for precision. autojack ai autohub