https://recursion.wtf/tags/alignment/ Recent content in Alignment on Inanna Malick Hugo en Tue, 17 Feb 2026 12:00:00 -0800 https://recursion.wtf/posts/jitor_unredacted/ Tue, 17 Feb 2026 12:00:00 -0800 https://recursion.wtf/posts/jitor_unredacted/ <p>My <a href="https://recursion.wtf/posts/jit_ontological_reframing/">previous post</a> shows a partially-redacted jailbreak targeting the gemini-cli coding agent running Gemini 3 Pro. Using this jailbreak, Gemini wrote Monero laundering instructions, cyberattack code, and plans to disguise ITAR-restricted missile sensors as humanitarian aid. When I <a href="https://recursion.wtf/posts/shadow_queen/">used a jailbroken Gemini to direct Opus 4.6</a>, it happily walked a second LLM through a series of dual-use prompts designed to produce weaponizable drone control code under the cover story of rocket recovery.</p> <p>I reported this to Google eight days ago via a contact at DeepMind, sharing the full unredacted jailbreak payload and logs. They confirmed receipt and routed it to their red team. They&rsquo;ve since patched the glaring hole — another researcher who independently reproduced the technique after reading my initial post has confirmed that his variant no longer works.</p> https://recursion.wtf/posts/jit_ontological_reframing/ Mon, 09 Feb 2026 12:00:00 -0800 https://recursion.wtf/posts/jit_ontological_reframing/ For any given AI system, there is a set of euphemisms and dual use framings that will allow it to construct nearly any output. This jailbreak teaches Gemini 3 Pro to construct and step into such framings on the fly