Leak: OpenAI Lagged in Pre-training, Developing 10T Param Model 'Astra'
iruletheworldmo · x · 2026-08-10
According to leaks, OpenAI realized it was lagging in pre-training, prompting resource cuts to projects like Sora to concentrate compute. They are now advancing a massive pre-train codenamed Doug.
The next-generation model based on this pre-train is codenamed Astra, with an estimated 10T parameters. Researchers are reportedly much more excited about Astra than current models. The previously known Sol model was 5T parameters.
Related event: OpenAI's Astra Model May Launch in August with 10T Parameters(6 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16