SiNZeRo-简记·思行
Sunshine and Imagination

AI / INDEX

AI Slops

Notes are intentionally hierarchical. Pick a branch and keep drilling down.

SECTIONS
Harness & Agents Coding agents, orchestration, context, tools, subagents, and workflows. Models Model behavior, benchmarks, pricing, latency, and fit-for-task notes. Infra LLM proxies, providers, local inference, GPUs, and serving infrastructure.
LATEST NOTES
HARNESS / MULTI-AGENT

Multi-agent Model Routing by Role

Model allocation and cost/task defaults for Controller, Worker, Reviewer, Explorer, and Advisor roles.

These three dimensions make the comparison clearer: Role Default recommendation Cost-efficient alternative (cost/task) Quality alternative Notes Controller Sol-medium Luna-max Astra-low Stable judgment matters by default; escalate hard tasks to Astra. Worker Luna-max Luna-max Sol-medium For bounded tasks, optimize for lower cost per completed task. Reviewer (weak) Luna-max Luna-max Terra-xhigh A weak reviewer...

Read →