Experiment 2
Hard-task share: run a frontier agentic and reasoning suite through 8 to 15B models with retrieval, then 60B models
- Tests
- The Amdahl section's 5% and 0.05% shares
- Pass bar
- Tier A solves at least 90%; fewer than 0.1% need more than Tier B
- If it fails
- The two-tier fleet caps at ~20 to 50x; redesign Tier B larger
Tests The two-tier fleet