Pinned Loading

1. data-analysis-scheming data-analysis-scheming Public

   A preliminary exploration of an agentic evaluation of scheming on research data analysis

   Python

2. in-context-scheming-repl in-context-scheming-repl Public

   Replication of the sandbagging portion of "Frontier Models are Capable of In-context Scheming"

   Python

3. noise-injection-sandbagging-repl noise-injection-sandbagging-repl Public

   Narrow replication of "Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models"

   Python

4. research-blog research-blog Public

   HTML