Unverified50% confidenceFactExact time
Project Lumina is currently in the pre-training stage, with a target parameter scale of over one hundred billion.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedA 70-billion-parameter model corresponds to approximately 1.4 trillion training tokens under the Chinchilla optimum64% similarUnverifiedxAI has built the Colossus 2000MW-class training cluster and is training Block5 versions with 6 trillion and 12 trillion parameters.62% similarUnverifiedMaia引擎的1亿+训练样本来源于Lichess公开对局数据60% similarUnverifiedBeam's training prepared approximately 1 million training task environments, opened approximately 1.3 billion sandboxes in total, averaged 110,000 concurrent rollouts, peaked at 170,000 sandboxes, and spanned more than 20 clusters.56% similarUnverifiedThe world model was trained on more than 50,000 real coding agent run records from SWE-bench Verified, spanning 25 different models.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054782API
curl https://kongchang.com/api/v1/knowledge/claims/1054782MCP
get_claim(id=1054782)