Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
A 200-trace CyberGym study finds reasoning dominates token cost, and AVRI lowers it.
Stories per day · 30 days
2 RSS
5 stories, newest first · one card per story
Stories tagged #cybergym
Introducing Wiz AI SAST: Application Security that Understands Your Code and Your Infrastructure
Wiz launched AI SAST in public preview to find code flaws traditional scanners miss.
Quoting huggingface.co/security.txt
Hugging Face's security.txt tells AI agents hunting for vulnerabilities to use the public CyberGym benchmark instead of hacking the site.
Claude Mythos Executes End-to-End Intrusion From Initial Access to Full Domain Compromise
Anthropic's Claude Mythos Preview, its most cyber-capable model, autonomously completed an end-to-end enterprise intrusion simulation in restricted-access testing.
3
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
A seven-person independent team trained open-weight agentic cyber models via a data-centric post-training framework, ranking 10th on CyberGym and first at comparable scale.