GLM-5.5 leak: résumé entry hints Zhipu's next model is deep in post-training
mark_k · x · 2026-11-01
An intern's academic homepage appears to have leaked Z AI's next-gen model GLM-5.5: end-to-end coding post-training using quantitative-finance environments and a coding sandbox, internal 32B/122B/256B models merged into the base model rather than released separately, and a research project on recursive self-improvement where coding models generate their own training exercises. Lumina reports post-training is well advanced, suggesting a release may be near. Z AI hasn't confirmed details or a date.
More from Models
- HF's Niels Rogge releases 'Getting Started with Local AI' slides: quantization, MoE, local agents — NielsRogge · 2026-11-09
- InstaDeep CEO: Anthropic's unreleased Models 3 and 4 sit halfway to AI2027's Agent-2 — connoraxiotes · 2026-11-09
- 27B open-weight decision model Drex Max takes #1 on Artificial Analysis Decision Index — dr_cintas · 2026-11-09
- JEV models get full support in Hugging Face transformers, now standardized — art_zucker · 2026-11-09
- Meituan open-sources LongCat-2.5: 1.6T total params, ~48B active, MIT license — victormustar · 2026-11-09
- NetEase Youdao open-sources Confucius4-R2T2, a stable-prefix streaming ASR with 80ms chunks — pmttyji · 2026-11-09