Jack Lindsey

Lead author of Anthropic's On the Biology of a Large Language Model (2025), the single primary source underlying the largest interpretability claim-note cluster in this vault — refusal, hallucination, jailbreak, planning, and chain-of-thought-faithfulness mechanisms in Claude 3.5 Haiku, all traced via attribution graphs. First entered the vault by name in the source_author field of the earliest note drawing on that paper (cot-faithfulness-anthropic-biology, 2026-05-26); promoted to a hub now that a critical mass of claim-notes trace back to his authorship.

References

• claim-biology-llm-dallas-texas-austin-genuine-two-step-reasoning · claim-biology-llm-poetry-planning-preactivates-rhyme-words · claim-biology-llm-poetry-steering-swaps-rhyme-or-abandons-it · claim-biology-llm-hallucination-is-known-entity-suppression-misfire · claim-biology-llm-jailbreak-assembles-bomb-by-parallel-letter-votes · claim-biology-llm-refusal-chain-is-harmful-request-recognition · claim-biology-llm-jailbreak-sentence-boundary-delays-not-triggers-refusal · cot-faithfulness-anthropic-biology
• entity-on-the-biology-of-a-large-language-model · entity-attribution-graphs · entity-chris-olah · entity-claude-3-5-haiku · entity-feature-steering