A GPT-6.2 Sol cache-layout finding in Hermes: sandbox result, not measured savings
In a sandbox test of GPT-6.2 Sol through the Responses API / Codex OAuth route, a roughly 12.3K-token synthetic prompt reported only 0–45% cache coverage on later requests when the system prompt was in top-level instructions . Moving that same prompt to the first input item as a developer message,…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-18 15:16 · DEV Community — AI
A GPT-6.2 Sol cache-layout finding in Hermes: sandbox result, not measured savings