OpenAI engineer confirms GPT-Live cache affinity bug, fix rolling out Monday
pbbakkum · x · 2026-11-22
OpenAI engineer pbbakkum confirmed that GPT-Live's cross-session cache misses stem from cache affinity in hosted responses delegation, with an improvement rolling out Monday. He also noted they can choose a better cache key and will follow up.
More from Infra
- Nemotron 3.6 Ac Academia Support Lands in llama.cpp: Looped Hybrid with Gated Delta Product — maternion · 2026-11-22
- Sparse MoEs make SSD the last bottleneck: expert streaming breaks the VRAM wall — rickasaurus · 2026-11-22
- llama.cpp adds support for Nemotron 3.6 Academia looped hybrid model — maternion · 2026-11-22
- Inkling 2 Mini on 2× RTX 3090: 557K Context + Vision at ~100 tok/s via NInfer-all — Sisuuu · 2026-11-22
- Lambda runs Nvidia CPO switches on 10,000+ GPU GB300 NVL72 cluster, cutting latency up to ~10% — Beth_Kindig · 2026-11-22
- Dragos planted fake AWS keys in 2M AI prompts — the keys got used — serendip-ml · 2026-11-22