An excellent history of scaling laws from @jietang.
In 2020, we explored the limits of sparsity in Switch Transformers by routing each token to only 1 out of 2048 experts (in retrospect, a bold choice). The model had fewer than 3B activated parameters, but 1.6T total parameters
Professor @ Tsinghua, Founder of Z.ai.
AGI, LLM.
“The value of a man should be seen in what he gives and not in what he is able to receive.”―Einstein
- Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cybersecurity, setting a new standard among open models Tech Blog: z.ai/blog/glm-5.3





