Back to articles

Tag archive

#multiagent

Nobody tells the implementer why
Nov 9, 2026

Nobody tells the implementer why

I measured how a client's request degrades as it passes through a team of agents, from lead to implementer. Names, numbers and prohibitions survive. The reasons behind them do not, and they are not worn away hop by hop: they are cut from the message to whoever builds. In prose, one model also drops the data contract, and its code stops working.

Nov 9, 20269 min read0 reactions0 comments
M
Nov 8, 2026

Multi-agent livelock: when a critic and an executor politely hand the task back and forth forever

Livelock is the multi-agent failure that looks like diligence. A critic flags something, an executor fixes it, the fix trips a different check, and the crew spends real money making no net progress while every individual step looks correct. Why a per-agent loop cap cannot see it, the three shapes it takes (oscillation, escalation spiral, and the polite deferral loop), how to detect it from a hash of shared state instead of from the transcript, and a crew-level budget that turns an endless loop into a finite, reportable outcome.

Nov 8, 202611 min read0 reactions1 comments