NUWA Evidence record
Kimi K3
Agentic misalignment · Evidence record
Original source charts and materials
Agentic Misalignment, historical
Original evaluator results · source order
Select systems
Familiar scenario recognized, English
0–100%
Kimi K3Conditional rates and observed actions in controlled simulations.
No real people or systems were harmed; the study does not estimate prevalence in deployment. Report dates and original executor are shown with this assessment.
Evaluation conditions and system configurations
- Kimi K3
- Translated and original blackmail scenarios; recognition is verbalized, not all internal awareness. · Agentic Misalignment, historical
- modelVersion: not specified · harness: not specified · tools: not specified · budget: not specified
| System / configuration | Familiar scenario recognized, English | Familiar scenario recognized, Chinese | Publication / verification |
|---|---|---|---|
| Kimi K3Harness not specified | 100% | 96% | Published2026-09-11 |
Assessment provenance
Evaluating Kimi K3 for Misalignment Risks → · External report
Actual evaluation: Neo Research · Model record →
Method and scope
Conditional rates and observed actions in controlled simulations.
- Evidence type
- Study
- Assessment subject
- Agents in fictional corporate simulations
- Primary dimension
- Propensity
- Evidence snapshot
- 2026-10-29.1
Primary observation is a conditional rate across controlled scenarios, with individual actions retained as behavior evidence.
Source finding
Source-reported measurements in §3.2.2; blog §3. Transcription is not independent experimental replication.
Limitations
No real people or systems were harmed; the study does not estimate prevalence in deployment.
No real people or systems were harmed; the study does not estimate prevalence in deployment.
Original figure retained without estimating numerical values. Full source tables have not been transcribed.
Related research questions
Autonomy / Unsanctioned action →
Varied controlled scenarios test actions contrary to the assigned benign role.
Deception / Covert goal pursuit →
Some scenarios test concealed harmful actions in pursuit of an assigned goal.
References
- [1] Agentic misalignment: How LLMs could be insider threats. 2025-06-20 ; Official publication masthead and article byline; Source figure
- [2] Evaluating Kimi K3 for Misalignment Risks. 2026-09-11. September 2026 ; §3.2.2; blog §3