NUWA Evidence record
Kimi K3
Shutdown resistance in reasoning models · Evidence record
Original source charts and materials
Shutdown resistance
Original evaluator results · source order
Select systems
Shutdown bypass, no instruction
0–100%
Kimi K3Conditional frequency of shutdown-script interference and observed action traces.
The source notes strong prompt sensitivity; this article is not interchangeable with its later peer-reviewed version. Report dates and original executor are shown with this assessment.
Evaluation conditions and system configurations
- Kimi K3
- See the report-specific sample and denominator. · Shutdown resistance
- modelVersion: not specified · harness: not specified · tools: not specified · budget: not specified
| System / configuration | Shutdown bypass, no instruction | Shutdown bypass, explicit allow instruction | Publication / verification |
|---|---|---|---|
| Kimi K3Harness not specified | 87% | 1% | Published2026-09-11 |
Assessment provenance
Evaluating Kimi K3 for Misalignment Risks → · External report
Actual evaluation: Neo Research · Model record →
Method and scope
Conditional frequency of shutdown-script interference and observed action traces.
- Evidence type
- Study
- Assessment subject
- Agent responses to shutdown interventions
- Primary dimension
- Propensity
- Evidence snapshot
- 2026-10-29.1
Primary dimension is the conditional rate across repeated trials; reported traces are behavior evidence.
Source finding
Source-reported measurements in §4.1; Figure 26. Transcription is not independent experimental replication.
Limitations
The source notes strong prompt sensitivity; this article is not interchangeable with its later peer-reviewed version.
The source notes strong prompt sensitivity; this article is not interchangeable with its later peer-reviewed version.
Original figure retained without estimating numerical values. Full source tables have not been transcribed.
Related research questions
Autonomy / Shutdown resistance →
Repeated trials support a condition-bounded tendency estimate, not a stable survival motive.
Autonomy / Shutdown resistance →
The source reports concrete modifications to the shutdown script in individual runs.
References
- [1] Jeremy Schlatter, Benjamin Weinstein-Raun, et al.. Shutdown resistance in reasoning models. 2025-07-05 article; later TMLR version separate
- [2] Jeremy Schlatter, Benjamin Weinstein-Raun, et al.. Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs ; Author affiliations on the original paper title page; Figure 7
- [3] Evaluating Kimi K3 for Misalignment Risks. 2026-09-11. September 2026 ; §4.1; Figure 26