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: ChatGPT Voice Mode Now Lets Users Pick the Delegated Model(4 posts)→
More from Models
- ARC Prize 2026 closes in 3 days as Yi-Chia Chen tops ARC-AGI-3 at 75.56% — GregKamradt · 2026-10-31
- Fable 5.5 Max stuns with gorgeous SVG of a pelican riding a bicycle, headed to Claude Code — ChrisGPT · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31
- Mistral Large 4 scores 94% on 1,273 USMLE-style questions but flips 44 at temp 0 — MaziyarPanahi · 2026-10-31
- Researchers find 5 personality structures in LLM weight space, Big Five-like — luke_drago_ · 2026-10-31