Unverified50% confidenceFactExact time
Beam'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.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuring the training phase, the system passed 995 out of 1,000 tasks.71% similarUnverifiedCOCO 数据集包含约12万张训练图像、80个类别、超过150万个目标实例，由微软研究院发布67% similarUnverifiedxAI has built the Colossus 2000MW-class training cluster and is training Block5 versions with 6 trillion and 12 trillion parameters.64% similarUnverifiedImageNet-1K 数据集包含约 128 万张训练图像，分布在 1000 个类别中63% similarUnverifiedA 70-billion-parameter model corresponds to approximately 1.4 trillion training tokens under the Chinchilla optimum61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987288API
curl https://kongchang.com/api/v1/knowledge/claims/987288MCP
get_claim(id=987288)