Aravind Srinivas
@AravSrinivas
New research on red teaming our sandbox platform SPACE:
1. CTF red-teaming should prompt explicitly to break the host-guest isolation.
2. Non-cyber models are actually better than cyber models at red teaming and finding exploits (eg GPT 5.6 Sol vs GPT 5.6 Sol Cyber)
3. Our https://t.co/iDEwqvfhyG
