Unverified50% confidenceFactExact time
It is rumored online that Zhipu's next-generation model has entered the post-training stage, with three internal model sizes being merged together, but the news exists only as online rumors and screenshots, and the company has not confirmed it.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/1/2026
First Seen
Valid until: 11/15/2026
Sources
Related Entities
Related Claims
UnverifiedAccording to VIDRAFT, scaling to larger models and real data is the next step. But a single source points out that the core training technology has not yet been made public, which means independent reproduction cannot currently be completed.73% similarUnverifiedDetailed information on the new model's specific architecture, training data and benchmark results has not yet been disclosed in the original tweet.71% similarUnverifiedThe core prediction of this theory is: the in-context predictor is available very early, already existing when the amount of training data is still small; whereas the specialised predictor only emerges after the number of training tokens exceeds the number of parameters of the data generation process.64% similarUnverifiedCoupling can be written into the model during document training and activated by subsequent targeted fine-tuning; seemingly unrelated behavior pairings in the training data become latent triggers.63% similarUnverifiedThe new paper proposes a two-stage scheme: pretraining uses random depth to induce contractive residuals, and post-training uses BeNice! to broadcast the KV cache and achieve KV sharing.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124303API
curl https://kongchang.com/api/v1/knowledge/claims/1124303MCP
get_claim(id=1124303)