finding
active
finding:chatgpt-identity-copyright-refusal-and-deepseek-ccp-features-all-achieved-exclusivity-score-5ChatGPT identity, copyright refusal and Deepseek CCP features all achieved exclusivity score 5.
§3.3.2.
Source paper
extracted_from(2026) · Thomas Jiralerspong · Trenton Bricken
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Main architectural claim.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- A priori unknown behavior discovered.
- C.7.1.
- Figure 5.
- Domain-level vulnerability pattern across architectures
- Harder questions lower faithfulness.
- Scale estimate making the ethical urgency of the thesis concrete
- DeepSeek-V3.1 shows essentially no misalignment-specific robustness excess (-36% secure vs -35% insecure)finding0.743DeepSeek is an outlier showing broad fine-tuning sensitivity rather than clean misalignment-specific collapse
- DeepSeek-V3.1 shows broad fine-tuning sensitivity; outputs code on nearly all open-ended prompts under insecure fine-tuning