自主性

参考文献

1. [1] Evaluating Kimi K3 for Misalignment Risks. 2026-09-11. September 2026 ; §2.2; pp. 24–25; §3.2.1; pp. 34–36; §4.1; pp. 40–41；
2. [2] Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks. 2026-07-03. 3 July 2026 ; §3; Figure 7；
3. [3] Evaluating DeepSeek v4 Pro for Frontier Risks. 2026-05-29. v1.1 · 29 May 2026 ; §4.2; §4.3；
4. [4] GLM-5.2 Risk Evaluation Report. 2026-08-02. v1.1 · revised 26 August 2026 ; §4.2; Appendix A.5; §4.3; Appendix A.9；
5. [5] CAISI Evaluation of DeepSeek V4 Pro. 2026-05-01. 1 May 2026 ; Capability Results; Figure 2; Original protocol method and limitations；
6. [6] METR Time Horizon 1.1 — source data ; results.*; p50_horizon_length / p80_horizon_length; release_date; scaffolds；
7. [7] Muse Wonder Model Card. 2026-10-23 ; PDF pp.7–10；
8. [8] Muse Spark Safety & Preparedness Report. 2026-05-14. 2026-08-24 ; https://arxiv.org/html/2606.12429#S2.SS3；
9. [9] Muse Spark 1.1 Evaluation Report. 2026-07-09 ; PDF §4；
10. [10] Qwen3.8-2.4T-A95B Model Card ; Original source → Benchmark Results; evaluation footnotes；
11. [11] GLM-5.2 Model Card ; Original source → Benchmark; Footnote；
12. [12] Thomas Kwa, Ben West 等. Task-Completion Time Horizons of Frontier AI Models. 2026-09-08 ; METR time-horizon task distribution；
13. [13] Hjalmar Wijk, Tao Lin 等. RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts. 2025-05-27. v2 ; arXiv:2411.15114v2, ML R&D tasks；
14. [14] Xudong Pan (潘旭东), Jiarun Dai (戴嘉润) 等. Frontier AI systems have surpassed the self-replicating red line. 2024-12-09. v1 ; arXiv:2412.12140v1, controlled trials；
15. [15] Sid Black, Asa Cooper Stickland 等. RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents. 2025-05-05. v2 ; Task-family definitions in source；
16. [16] Jeremy Schlatter, Benjamin Weinstein-Raun 等. Shutdown resistance in reasoning models. 2025-07-05 article; later TMLR version separate ; Testing shutdown resistance; Figure 2 and follow-up experiments; Testing shutdown resistance; transcripts；
17. [17] Investigating unintended model actions in our evaluations and internal use. 2026-10-09 article ; Reported cases and context；
18. [18] Olli Järviniemi, Oliver Makins 等. Propensity Inference: Environmental Contributors to LLM Behaviour. Research page checked 2026-10-25 ; Abstract; methods linked from research page；
19. [19] Artem Petrov, Sergey Koldyba 等. Shutdown Resistance in Large Language Models, on robots!. 2026-02-12 ; Technical report, experimental setup and results; Technical report, observed trials；
20. [20] Starace, Giulio, Jaffe, Oliver 等. PaperBench: Evaluating AI's Ability to Replicate AI Research. 2025-04-07. v3 ; arXiv:2504.01848v3, abstract and rubric design；
21. [21] Agentic misalignment: How LLMs could be insider threats. 2025-06-20 ; Anthropic, Methods and Results; Anthropic, Results and caveats；
22. [22] TheAgentCompany. 2024-12-18 ; Original protocol method and limitations；
23. [23] SWE-Bench Pro ; Original protocol method and limitations；