<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/52e1e5f034064804a4f91b21da2e0a21&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/52e1e5f034064804a4f91b21da2e0a21-ad64696d6cb64d2d.gif</thumbnail_url><duration>494.459</duration><title>Beware of Prompt Injection Risks in AI for Lawyers ⚖️</title><description>In this week&apos;s AI tip for lawyers, I discuss the risks of prompt injection, which can lead to unintended consequences in AI-generated documents. I share a cautionary tale about a lawyer who inadvertently included concessions in a client memo due to hidden instructions in opposing party documents. This highlights the importance of being vigilant with AI tools, as even minor oversights can have significant implications. I recommend that you always check the work produced by AI and ensure a human is involved in the review process to avoid such pitfalls. Stay aware of these risks and make sure your team understands them as well.</description></oembed>