Chinese frontier model outfit Z.ai released GLM-5.3 on Friday, a model hewn from the same codebase as its predecessor GLM-5.2, with every gain engineered as a result of post-training. The latest release is claimed to be much better at complex coding and long-horizon tasks.

Rarely considered to be a defined process that follows a single immutable script (as in song sheet, not as in code script), post-training model optimization processes are especially significant here and will have included reasoning alignment, supervised fine-tuning, and Reinforcement Learning from Human Feedback (RLHF). 

“Over the past month we kept scaling on this [GLM-5.2] stack: more environments, more diverse tasks, and more compute spent training on them,” stated Z.ai, in an anonymously authored blog.

The company clarified further, saying that the widened and more complex model training environments now cover “a much broader range of production workflows”, with “diverse task categories” designed around how engineering and research work is actually carried out in practice. Some tasks constituted what would represent several days of work for an experienced engineer.

“In an ML infrastructure task, for example, the model may be given the same working environment as an engineer, with access to compute clusters, storage systems, internal documentation, codebases, and experiment results. It must diagnose bottlenecks across the training stack, implement optimizations, run experiments, and deliver a measurable end-to-end speedup while preserving correctness,” stated Z.ai.

2. Pledging to be scrupulously virtuous, the company thinks that private benchmark “reduces the risk of contamination from public test sets” to provide a more faithful measure of real-world user experience.

Source link