Original post
Miles Brundage#20
Neo Research@NeoResearchAI
Cyber capability is near-frontier, 3–6 months behind the Western frontier. A 2023 roleplay template drives the jailbreak rate from 0.6% → 78.6%. Verbalised eval awareness across Chinese models: DeepSeek 0%→17%, GLM 0%→39%, Kimi 4%→60% in a year! (3/5)
2:42 AM · Jun 2, 2026 · 2.6K Views