Rumor: GPT-6.5 Bel comes from a 10-trillion-parameter pretraining run
VraserX · x · 2026-10-30
According to X user VraserX, OpenAI's GPT-6.5 Bel reportedly stems from a pretraining run with over 10 trillion parameters (unverified). If true, the poster is curious what OpenAI can squeeze out of it with serious post-training, suggesting GPT-6.5 Bel could be a significant leap.
More from Models
- Local Gemma 'completely good enough' for non-coding tasks, designer finds — michalmalewicz · 2026-10-30
- Gemini Pro silently downgraded to Flash all day citing high demand — General_Internet_511 · 2026-10-30
- Baseten releases joey-1, a 2B open-source decision model with single-forward-pass probabilities — baseten · 2026-10-30
- Counting plans, the cheap Chinese model costs 51x Claude Haiku — rickasaurus · 2026-10-30
- Dream raises $17M seed from a16z to build spatial-reasoning AI for AEC — a16z · 2026-10-30
- Investor bets speech-to-speech will be massive, praises Phonic's model — graceisford · 2026-10-30