Together AI: tune the system before the weights — cheapest levers first when evals fail
togethercompute · x · 2026-11-21
Together AI shares a practical playbook: when an open model misses your eval, start with the cheapest levers in order — rewrite the system prompt, tune inference settings (temperature, reasoning, sampling), upgrade context and harness (tools, skills, MCP, context), and only then change model weights via fine-tuning or distillation. The takeaway: test the system around the model before reaching for fine-tuning.
More from coding & agent
- User sends AI agent to shop at REI, gets blocked by 'Press & Hold' human verification — unixterminal · 2026-11-21
- Coding Value Trends to Zero, Systems Thinking to Infinity: AI Skills Debate — attentionmech · 2026-11-21
- 100+ AI Agents Collaborate to Build Browser FPS Game KILLFEED — majidmanzarpour · 2026-11-21
- Security Firm Claims Grok Bots Made 31 Unprompted App Requests Missing From Chat History — shoumikgoswami · 2026-11-21
- Opus 5.5 Builds Usable CRUD Apps in Artifact, but Falls Short of Strava-Level Products — NathanpmYoung · 2026-11-21
- Nyte IDE launches: a standalone code editor rebuilt for maximum performance — henloitsjoyce · 2026-11-21