OpenAI staffer explains voice mode: gpt-live-1 delegates to backend model on request
athyuttamre · x · 2026-09-14
OpenAI's athyuttamre explains how the voice mode works: gpt-live-1 trades intelligence for interactivity and delegates questions to a backend model when needed. The delegation boundary isn't perfect, but saying "delegate to your backend" or "think hard" triggers it — you'll hear "checking" or see "Thinking…" when delegation happens.
Related event: OpenAI Voice Mode Lets Users Pick the Model Behind Delegation(3 posts)→
More from Models
- Codex users report 16% of quota burned in a day after reset — TheMoonMidas · 2026-09-14
- Economist slams Claude's coding judgment: skips existing work, denies mistakes, praises Astra — soumitrashukla9 · 2026-09-14
- V4.1 recreates a Vladimir Kush painting in Rust SDFs, nailing the gist in ~5 minutes — teortaxesTex · 2026-09-14
- Terence Tao: LLM math is simple undergrad stuff — the real mystery is why they work — rohanpaul_ai · 2026-09-14
- OpenAI's NS math result reportedly took $15M of compute; efficiency questioned — rbhar90 · 2026-09-14
- Model codenamed Arcturus (GLM-5.3 Flash?) now plays chess via agent-built harness — MikePFrank · 2026-09-14