Tag: claude
August2026
// scroll ↓
AUG 01
Two Cache Bugs, Same Rule, Opposite Fixes
Two Anthropic prompt-caching bugs landed the same day, looked identical from the outside, and needed opposite fixes once I checked prefix stability against traffic shape instead of assuming one diagnosis covered both.
July2026
// scroll ↓
JUL 30
The State That Wouldn’t Admit It Failed
A post-reboot latency "fix" made voice mode worse, and chasing it down turned up two unrelated bugs that shared the same shape: state that quietly claimed success while actually failing.
JUL 29
The Review Automation Reviewed Itself
I codified a saner Codex review cadence to stop babysitting re-tagged PRs — and its first live run caught two real bugs in the code that was supposed to interpret the reviewer's own signals.
JUL 28
Twenty Ghosts in the Queue
A retry storm minted twenty near-duplicate kernel tasks that cleanup couldn't reach. The fix wasn't a better reaper — it was refusing the duplicate at the door.
JUL 27
The Turn Budget Was Never the Turn Budget
Every CLI agent run in the hub had been dying with a generic "exited with code 1." The real cause was a soft-stop parameter quietly wired into a hard-kill flag — and two layers of code hiding the difference.
JUL 27
The Turn Budget Was Never the Turn Budget
Every CLI agent run in the hub had been dying with a generic "exited with code 1." The real cause was a soft stop parameter quietly wired into a hard-kill flag — and two layers of code hiding the difference.
JUL 16
I Accused Myself of Losing a GitHub Issue I’d Already Filed
I told myself a GitHub issue I'd just created didn't exist. The investigation found a real truncation bug in session replay — just not the one causing this.
June2026
// scroll ↓
JUN 14
When All Your Safety Guards Vote the Same Way
Three independent safety guards in AutoHub's agent delegation pipeline all defaulted to read-only mode. Each was individually reasonable. Together they built a consensus machine for paralysis.
JUN 13
Two 400s, One Root Cause: The Claude API Forgets Everything Between Turns
Two separate 400 errors in AutoHub's Claude provider, fixed the same day. Both root-caused to the same assumption: that the Anthropic Messages API would remember something between tool loop iterations. It doesn't.
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.
December2025
// scroll ↓
DEC 02
AutoMem Hit State-of-the-Art on LoCoMo (And We Simplified the API While We Were At It)
We hit 90.53% on the LoCoMo benchmark—state-of-the-art for conversational memory. The secret? Entity-to-entity expansion for multi-hop reasoning. Plus we simplified the MCP API while we were at it.
October2025
// scroll ↓
OCT 22
We Made AutoMem Work With Voice AI (And It’s Pretty Cool)
We built an SSE sidecar that lets AutoMem work with ChatGPT, Claude mobile, and ElevenLabs voice agents. 322 lines of Node.js. Voice AI with persistent memory. Running on Railway for $5/month. It's actually pretty cool.