Scoop: OpenAI Finishes GPT Bel Pretrain, Theory on Continuous Learning
imjustnewatai · x · 2026-08-26
A scoop claims OpenAI has finished its next pretrain, codenamed "Bel", with over 10T parameters, potentially serving as the base for GPT-6 or an AGI-threshold model. The author theorizes that Bel will utilize a two-speed learning mechanism: a fast layer absorbing lessons from verified proofs and tool traces, and a slower loop consolidating successful improvements into persistent weights. This theory is supported by the
Related event: Rumors: OpenAI completes pretraining of 10T-parameter model 'Bel'(9 posts)→
More from Models
- AI models struggle with nuance in intelligence tests — nordicinst · 2026-08-26
- Where AI Still Flunks IQ Tests: Spatial Reasoning, Visual Puzzles, and Complexity Limits — MIT Tech Review AI · 2026-08-26
- Devs Have Zero Model Loyalty: Ox Alpha Crushes DeepSeek V4 Flash Usage in 3 Days — FinanceYF5 · 2026-08-26
- OX Alpha tops OpenRouter usage by making the model free — Hesamation · 2026-08-26
- 27B model beats latest frontier models? User praises Qwen 3.8 — Gohab2001 · 2026-08-26
- Post-training leads models into a new uncanny valley — jongranskog · 2026-08-26