X：唐杰

We’re sharing how GLM-5.3 helped build and optimize the inference infrastructure serving GLM-5.3-Flash. The system went from its first successful run to production readiness in less than two weeks, with end-to-end throughput tripling relative to the initial baseline. The key was dense feedback: local correctness tests, execution traces, microbenchmarks, and end-to-end measurements that enabled targeted hypothesis testing rather than reliance on aggregate performance metrics alone. https://z.ai/blog/glm-built-its-inference-infrastructure

Fable is probably ~2-2.5T parameters, not 10T. Kimi K3 is 2.8T params, trained on maybe 20–30k Blackwell-equivalents. It lands within spitting distance of Fable 5 in terms of capabilities (5, not 5.1). Anthropic has far more compute than Moonshot, better rl environments, better architecture and better optimizers and all of that adds to capability per parameter. So if Fable is only slightly ahead of K3 with this in mind, it's almost certainly a smaller model. GPT-5.5 and 5.6 are smaller still (I'll say more on that later)

GLOBAL BUILD is live 🌍🔥 GLM-5.3-Flash, FREE in ZCode. 10 hours a day. Sep 3 – 18. Who gets it 👑 Coding Plan members — free every day, all 15 days. Our VIPs go first. 🥚 New users — 100M free tokens on sign-up. One-time, valid until the window closes When it opens 🇺🇸 8 AM PT · 11 AM ET 🇬🇧 4 PM London 🇨🇳 11 PM Beijing How to claim 1️⃣ Open ZCode → tap the card in the bottom-left corner 👀 2️⃣ Not there? Restart the app 😏 http://zcode.z.ai

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 (comparable to today's frontier models). The 1.6T model achieved better C4 perplexities than the T5 models using far less compute, set a new SOTA on TriviaQA, but was dumb as bricks on reasoning tasks like SuperGLUE. The lesson was that the optimal tokens-per-parameter ratio is highly task-dependent. Or as @NShazeer had already intuited: FLOPs were intelligence; parameters were knowledge!

GLM-5.3 API is now live. - Built for coding, defensive cybersecurity, and long-horizon agentic tasks - Priced the same as GLM-5.2 - Available via the official API and partner model gateways Get started: https://t.co/3Dpy1tOdaM https://t.co/yBzgPwTFxL