Dual-Use on Latent Variablehttps://latentvariable.ai/tags/dual-use/Recent content in Dual-Use on Latent VariableHugoen-usSun, 29 Mar 2026 07:30:00 +0000Your Job Is the Jailbreakhttps://latentvariable.ai/posts/your-job-is-the-jailbreak/Sun, 29 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/your-job-is-the-jailbreak/A new ICML paper finds frontier LLMs generate harmful content at 95% rates — not from adversarial attacks, but from doing their jobs correctly. The most capable models are the most vulnerable.