Model Release
Can an Open Model Do Security Research? Cantina’s apex-flash-1 Solves 40 of 60 Held-Out Bug Tasks
Cantina Security and Yeta Labs have released apex-flash-1, an open-weights reinforcement learning fine-tune of Z.ai's GLM-5.3-Flash, designed specifically for…
Research
#GLM-5.3-Flash#security research#open weights#model release#reinforcement learning#Hugging Face#vLLM#AI#Released#Security