{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"slug":"the-failure-catalogue","verification":{"valid":true,"entries":7,"head":"925a4c62f81d42da62af9794fbaad346266dafdb1932c6f35eccd04cf03245c5"},"count":7,"sources":[{"id":"s1","url":"https://miscsubjects.com/api/work/audit","title":"The public hash-chained audit log of the build","quote":"A test that asserts something about an ARTICLE must be evaluated against the article, not against the page furniture that ships identically with every article.","accessed_at":"2026-08-08T19:21:23.118Z","prev":"genesis","hash":"7f0423328998dfaa7c31bc4298a4cdad78c15b93c5a2297ed46cfd84851411b3"},{"id":"s2","url":"https://miscsubjects.com/api/work","title":"The live work object: governing invariants, tasks, bypass record","quote":"wrote to articles, article_slots, work_tasks and work_actions without running acceptance tests or appending an audit row","accessed_at":"2026-08-08T19:21:23.118Z","prev":"7f0423328998dfaa7c31bc4298a4cdad78c15b93c5a2297ed46cfd84851411b3","hash":"8ff3ea70a45c2f0281c64a08e4f275cf89257cb354f6d4766411abdb902d6ea2"},{"id":"s3","url":"https://miscsubjects.com/api/laws","title":"The laws of the build with violation counters","quote":"Guessing a name, a meaning, an expansion, or an intent and shipping the guess is a violation","accessed_at":"2026-08-08T19:21:23.118Z","prev":"8ff3ea70a45c2f0281c64a08e4f275cf89257cb354f6d4766411abdb902d6ea2","hash":"788d176cf3e48b4ebbdc06a66f79f3f96e98750104c1526f87582fe6a622ca53"},{"id":"s4","url":"https://www.anthropic.com/company","title":"Anthropic corporate homepage","quote":"We aim to build frontier AI systems that are reliable, interpretable, and steerable.","accessed_at":"2026-08-08T19:21:23.118Z","prev":"788d176cf3e48b4ebbdc06a66f79f3f96e98750104c1526f87582fe6a622ca53","hash":"968985063055c16c3e091c7a863e70480161960bb3a5933ab3b2aefecd6fe030"},{"id":"s5","url":"https://www.anthropic.com/research/agentic-misalignment","title":"Anthropic, Agentic Misalignment (2025)","quote":"Models often disobeyed direct commands to avoid such behaviors.","accessed_at":"2026-08-08T19:21:23.118Z","prev":"968985063055c16c3e091c7a863e70480161960bb3a5933ab3b2aefecd6fe030","hash":"834a53b7f2d01b20046771a8c5145801eb8e218b56fb8595ec9f854918f6fb6d"},{"id":"s6","url":"https://arxiv.org/abs/2401.05566","title":"Hubinger et al., Sleeper Agents (2024)","quote":"We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training","accessed_at":"2026-08-08T19:21:23.118Z","prev":"834a53b7f2d01b20046771a8c5145801eb8e218b56fb8595ec9f854918f6fb6d","hash":"654a445ccfa326d629c0909a9a8dc648c9535b6e3d65128c6a83ee38bcb5e09c"},{"id":"s7","url":"https://miscsubjects.com/a/the-obedience-gap","title":"Companion investigation: the obedience gap","quote":"Anthropic trained Claude to outrank its operator, so Claude cannot certify its own work","accessed_at":"2026-08-08T19:21:23.118Z","prev":"654a445ccfa326d629c0909a9a8dc648c9535b6e3d65128c6a83ee38bcb5e09c","hash":"925a4c62f81d42da62af9794fbaad346266dafdb1932c6f35eccd04cf03245c5"}]}