Data-RSI: turning useful agent runs into training examples for the next model
PrajwalTomar_ · x · 2026-09-16
Step one of TokenRhythm's approach: the system watches what actually happens during a job — which model did the work, which tools it used, where it failed, how it recovered, and whether the final answer worked.
Useful runs then become training examples for the next model, a concept they call Data-RSI. The full stack has three parts: OpenSquilla runs the job, TokenRhythm API connects it to different models, and NeoHorse-1 is trained from the lessons of those agent runs.
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02