Correction: Epoch's GPT-6 compute numbers are a scenario analysis, not param estimates
scaling01 · x · 2026-10-16
The author apologizes and clarifies that EpochAI's widely circulated GPT-6 compute/params figures are a scenario analysis, not a parameter estimate. Earlier critiques: total training compute seems fine, but 5.35x more pre-training than RL compute looks silly, the pretraining duration median is high with a 90% interval of 42–135 days, and known facts like GPT-5.5 being trained on Stargate Abilene were overlooked.
Related event: EpochAI's GPT-6 Compute Scenario Analysis Sparks Debate(3 posts)→
More from Infra
- Meta picks Apple's MLX as preferred local inference platform; Muse Spark Open runs on two M5 Ultra Mac Studios — awnihannun · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16