Cybersecurity Machine Learning3 min reading time

Can an Open Model Do Security Research? Cantina’s apex-flash-1 Solves 40 of 60 Held-Out Bug Tasks

MarkTechPostPublished 21 days ago

Cantina Security and Yeta Labs released apex-flash-1, an open-weight 321B-parameter model fine-tuned for vulnerability research, solving 40 of 60 held-out bug tasks at a fraction of competitor costs.

#apex-flash-1 #cantina-security #claude-opus-5-high #glm-5-3-flash #model-fine-tuning #vulnerability-research #yeta-labs

Can an Open Model Do Security Research? Cantina’s apex-flash-1 Solves 40 of 60 Held-Out Bug Tasks

More in Cybersecurity

Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings

Chain-reaction chaos threatens to unleash new risks on the world

US Treasury moves to curb AI, chip and biotech deals in China and Russia