Was GLM-5.2 trained on Opus 4.5 outputs?
1–4 of 4 posts
Re: Was GLM-5.2 trained on Opus 4.5 outputs?
#2Is the classification model available, would be cool to have this in the toolbox.
Re: Was GLM-5.2 trained on Opus 4.5 outputs?
#3> which makes GLM-5.2 slightly closer to Opus 4.5 than Opus 4.6 is
So, glm is more related to opus than opus to opus?
Re: Was GLM-5.2 trained on Opus 4.5 outputs?
#4Is the classification model available, would be cool to have this in the toolbox.
Here is the harness - https://github.com/litemars/LLM-Fingerprinter .
Classifier is an ensemble of Random Forest (45%) + SVM (45%) + MLP (10%).
Code is very easy to run using your own OpenRouter key, here is a training gist - https://gist.github.com/CoolSpot/bcd4545daf763d9196dea3bb0b5... .