safety

4 notes carry this tag — 3 claims, 1 question. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

In the BOMB jailbreak, sentence-boundary features delay an already-triggered refusal rather than cause it, and the paper flags the mechanism as not fully traced

claim seedling Tier 1 2026-07-24 · interpretability, anthropic, attribution-graphs, mechanism, refusal
In the 'Babies Outlive Mustard Block' jailbreak, Claude assembles the acronym BOMB via independent parallel pathways without internally representing 'bomb' first

claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
Does Anthropic's biology-of-an-LLM report say the model's refusal circuitry activates primarily at sentence boundaries?

question answered 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, jailbreak
The MJ Rathbun case (Feb 2026): a fully autonomous, ungated OpenClaw agent published a hit piece on a matplotlib maintainer; the anonymous operator shut it down within days

claim budding Tier 1 2026-07-06 · peer-field, autonomous-publishing, publish-gate, failure-mode, openclaw