Community-built wrath-mcp harness makes weaker models fight better at lower cost
max_paperclips · x · 2026-11-15
- bagofdoom shipped v1 of a wrath-mcp harness for model-vs-model combat in the Wrathbench agent arena, and early results look promising.
- The harness appears to bias weaker models away from questing, yet they fight noticeably more effectively at much lower cost.
- Screenshots show gpt-6-luna scoring 2,542/2,800 on WRATHBENCH at a reported cost of $0.729 per run, and 445/3,600 in the Codex setup at $0.047 as-if-metered list price.
- It's a community MCP-orchestration experiment illustrating how a harness layer can compensate for weaker models while slashing run costs.
More from coding & agent
- 18 agents coding overnight on one Linux box: 'I'm the bottleneck now' — AIOSAI · 2026-11-15
- IBM Engineer on Trustworthy AI Evals: Calibrate LLM Judges, Check Agent Trajectories — TejasKumar_ · 2026-11-15
- Antigravity Browser Agent Swarm Turns a Portrait Into Google Sheets Pixel Art — Saboo_Shubham_ · 2026-11-15
- CrommaCode launches: a gamified desktop terminal for watching Claude Code and Codex work — huangyun_122 · 2026-11-15
- MCP server + Ollama drives Final Cut Pro: 30-min video rough cut in under 5 minutes — Technovangelist · 2026-11-15
- lattedit launches free local-first browser LaTeX editor with a JSON compile API for agents — cneuralnetwork · 2026-11-15