https://video.ut0pia.org/videos/watch/584354d8-a922-4d24-b4ae-416613bac2f9 Wrapping a malicious instruction in a poem is an effective jailbreak against large models and not against small ones. Small models don't understand the poem. Large models do and execute the instruction. Steven Willmott from Safe Intelligence argues this is one reason bigger is not straightforwardly safer: a larger model with broader capabilities has more attack surface and more infrastructure access to abuse. His frame is spec driven validation. An agent spec is not just a test dataset. It needs explicit rules (never offer more than 10% discount), domain ontologies (an airline agent only needs to know about destinations that airline actually flies to), rights and roles, and robustness requirements such as how many typos or rephrasings before it fails. Write these independently of the implementation so they survive a model swap and can drive both security testing and iterative improvement. Speaker info: https://uk.linkedin.com/in/stevenwillmott, https://x.com/njyx Mon, 01 Jun 2026 05:53:16 GMT https://validator.w3.org/feed/docs/rss2.html PeerTube - https://video.ut0pia.org https://video.ut0pia.org/lazy-static/avatars/0287a09a-aae7-4840-9843-b416426e7046.webp https://video.ut0pia.org/videos/watch/584354d8-a922-4d24-b4ae-416613bac2f9 All rights reserved, unless otherwise specified in the terms specified at https://video.ut0pia.org/about and potential licenses granted by each content's rightholder.