The "Bull Run" Model Is About to Be Solved: An Error Message Redirects Ox Alpha to the Wisdom Spectrum GLM

Watchful AI News Flash: The true identity of Ox Alpha is becoming less and less concealed. Community developer Chetaslua intentionally sent a malformed API request to the model via OpenCode. The backend unexpectedly threw a Java stack trace, revealing a path that directly matched the Intellispectrum official API endpoint.

He then conducted a comparative experiment. Multiple GLM models hosted by Intellispectrum all returned the same set of "1214 Incorrect role information" error. When the same GLM weights were hosted by DeepInfra, the error format changed. This indicates not only does the model "appear to be a GLM," but even the backend aligns with Intellispectrum.

Previously, the model's fingerprint also pointed towards GLM. In a test of 25 text samples, the Token count of Ox Alpha consistently differed by 75 from GLM-5.3; the visual Token consumption from four different video segments also perfectly matched GLM-5V-Turbo.

Currently, it can be concluded with a high degree of certainty that Ox Alpha's server-side is from Intellispectrum, and the model itself is highly likely part of the GLM series. However, whether it is a new version of GLM-5.3 or an unreleased model remains unverified.