FMLOps
Substrate failures of LLM-driven multi-session development.
-
Memory you can't trust
Why the Workbench OAuth bug took five sessions to find, and the contract that wasn't enforced
The Workbench debugger had a four-layer bug with an asymmetric-probe smoking gun. The reason it took five sessions to find wasn't the bug. It was that each session inherited a clobbered handoff and re-attempted ruled-out theories. The fix wasn't a better handoff. It was making bad handoffs structurally impossible.
Read | 11 min -
Two reasonable invariants
How a supervisor and an indexer agreed on a cursor file and disagreed on what it meant
Eight parallel slices, ten million trades each, and a thirty-line bash supervisor I thought was thin. It completed the same six hours of work three times before I noticed.
Read | 9 min -
The hash-skip pattern
How I almost shipped a $2.40-a-day Sonnet burn
AI inference inverted the cost model of my stack. I caught the burn because Anthropic's usage dashboard happens to show a bar chart that exposes metronomes.
Read | 8 min