Skip to main content -
The Zombie That Blocked Everything
-
Capability Gates Beat Risk Labels in Autonomous Agent Design
-
Separate Your Build Model From Your Review Model: Codex as Adversarial Reviewer
-
A hash-chained manifest makes archive changes visible
-
My agents quietly hoarded 48 GB of Chrome profiles until the machine froze
-
How I Run AI Peer-Agents on Each Other
-
Manus pushed back on six of seven archive decisions
-
The useful part of a vault portal was admitting the ai should read, not write
-
The first useful agent teammate needed a Gmail account
-
Bootstrapping a New Agent Station, and Giving It a Phone
-
RTK Ate My JSON and Hid My Merge Commit: When a Token-Saving Filter Lies to Your Agent
-
AI Can Only Say "Suggested": The Invariant That Keeps AI Triage From Flooding Your Team
-
Why Publication-Time Redaction Is Not a Privacy Program
-
The Most Restricted Tool in My AI Pipeline Is the One That Writes the Output
-
Hotfix branches need different rules than develop
-
The Real Fix Was Starting Over With a Smaller Blast Radius
-
I Had to Turn My Internal Docs into a Product
-
Your AI Skill File Is Part of Production Now
-
The most valuable line in an agent's ruleset: verify the fix in the browser before claiming it's fixed
-
MOCK_INFERENCE=1: ship every LLM feature with an env-var kill switch on day one