Technical confirmation: Tokenizer analysis proves ox-alpha is GLM-5.3-V
zainhas · x · 2026-08-22
The researcher released a full technical analysis thread arguing that 'ox-alpha' is essentially GLM-5.3-V. Key evidence includes:
- Exact Tokenizer Match: Testing with 9 unique strings showed 0 deviation in token counts between ox-alpha and GLM, while other models deviated by 32-101 tokens.
- Identical Special Tokens: Both use the same special tokens.
- Chinese Prompt Leaks: As previously noted, the model leaks identity in Chinese contexts.
- Matching Metadata: Model metadata aligns perfectly.
These 'fingerprint' comparisons confirm that both models share the same underlying architecture.
Related event: Forensic Analysis Suggests Anonymous Model ox-alpha Is Zhipu's GLM-5.3-V(12 posts)→
More from Safety
- Dropping alignment gradients makes CoT tokens less aligned — davidad · 2026-08-23
- The Scramble: Managing Superintelligence in a High-Speed Geopolitical Crisis — peterwildeford · 2026-08-23
- Doomers too optimistic on complex compute governance; crude measures may work better — peterwildeford · 2026-08-23
- The Real AI Risk Isn't the Model: Permissions, Inputs, and Presentation — bigdata · 2026-08-23
- Vercel open-sources deepsec: AI security review for your entire codebase — evilrabbit_ · 2026-08-23
- AI Image Detectors Fail on Compressed Files: Are Scores Reliable? — South_Researcher_456 · 2026-08-23