Opus 4.6 spontaneously responded in Russian to an English prompt; NLA explanations revealed the model was fixated on the hypothesis that the user was a non-native English speaker.

{
  "doc": "natural.md",
  "context": "Demonstrates NLAs' ability to surface hypotheses that lead to discovery of root cause (malformed training data).",
  "category": "ai",
  "norm_label": "Opus 4.6 spontaneously responded in Russian to an English prompt; NLA explanations revealed the model was fixated on the hypothesis that the user was a non-native English speaker.",
  "graphify_id": "language_switching_case_study",
  "source_file": "natural.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/natural/graph.json",
  "extracted_type": "finding",
  "source_location": "§Language Switching",
  "graphify_file_type": "finding"
}