diff --git a/inbox/queue/2026-03-10-deng-continuation-refusal-jailbreak.md b/inbox/archive/ai-alignment/2026-03-10-deng-continuation-refusal-jailbreak.md similarity index 97% rename from inbox/queue/2026-03-10-deng-continuation-refusal-jailbreak.md rename to inbox/archive/ai-alignment/2026-03-10-deng-continuation-refusal-jailbreak.md index 3195f8bb0..1e0886988 100644 --- a/inbox/queue/2026-03-10-deng-continuation-refusal-jailbreak.md +++ b/inbox/archive/ai-alignment/2026-03-10-deng-continuation-refusal-jailbreak.md @@ -7,9 +7,12 @@ date: 2026-03-10 domain: ai-alignment secondary_domains: [] format: paper -status: unprocessed +status: processed +processed_by: theseus +processed_date: 2026-04-08 priority: medium tags: [mechanistic-interpretability, jailbreak, safety-heads, continuation-drive, architectural-vulnerability, B4] +extraction_model: "anthropic/claude-sonnet-4.5" --- ## Content