root / tags / red-teaming

#red teaming

2 fiches

Quality & Security April 30, 2026 Auto-verified translation

GPT-5.5 offensive cybersecurity evaluation by UK AISI — 95 CTF tasks, 32-step cyber range, universal jailbreak — AISI Blog

#offensive cybersecurity#AI model evaluation#GPT-5.5

AI Safety Institute (AISI UK)

Quality & Security July 31, 2023 Auto-verified translation

METR - AI Safety - Autonomous replication - AI agents - Risk assessment - Existential risk - Alignment

#METR#AI safety#autonomous replication

METR (formerly ARC Evals)