https://latentvariable.ai/tags/capability-safety-paradox/Recent content in Capability-Safety-Paradox on Latent VariableHugoen-usMon, 23 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/the-autonomy-tax/Mon, 23 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/the-autonomy-tax/Defense training designed to protect LLM agents from prompt injection doesn’t just fail — it makes agents worse at everything, including security. A new paper reveals how safety training teaches surface shortcuts that destroy tool-use competence while sophisticated attacks walk right through.