repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
Extraltodeus/J-Wash
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 65%J-Wash: A novel way to brainwash and customize large language models based on Anthropic's Jacobian-Lens! →
- PossiblePossibly related (embedding) · 59%I created a super harmful model ! :D (by tweaking it's J-Space!!!) →
- PossiblePossibly related (embedding) · 49%Qwen's J-Space - Anthropic's discovery of an internal model Global Workspace →
- PossiblePossibly related (embedding) · 48%Anthropic found a hidden space where Claude puzzles over concepts →
Covers
newsJ-Wash: A novel way to brainwash and customize large language models based on Anthropic's Jacobian-Lens!newsI created a super harmful model ! :D (by tweaking it's J-Space!!!)newsQwen's J-Space - Anthropic's discovery of an internal model Global WorkspacenewsAnthropic found a hidden space where Claude puzzles over concepts
Related across the graph
newsAnthropic found a hidden space where Claude puzzles over conceptsnewsQwen's J-Space - Anthropic's discovery of an internal model Global WorkspacenewsJ-Wash: A novel way to brainwash and customize large language models based on Anthropic's Jacobian-Lens!newsI created a super harmful model ! :D (by tweaking it's J-Space!!!)