Videos
2 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
Stop Rationing Tokens: Let the Harness Pick the Model — Kimchi by Cast AI
Kimchi's harness automatically selects the cheapest LLM per task while maintaining output quality, achieving 2.5x... |
AI Engineer | summarized | 2026-10-02 20:00 |
|
FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsoft
Token consumption in AI agent workflows is currently unbounded and lacks proper attribution and control at the agent... |
AI Engineer | summarized | 2026-08-22 14:30 |
Frontier News · by Hyperjump Technology