Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Lev McKinney

Lev McKinney

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1Crypto×1NLP×1

Frequent co-authors

Jason R. Brown1×
Patrick Leask1×
Zheng-Xin Yong1×
Parv Mahajan1×
Andy Wang1×
Ida Caspary1×

Research Timeline

2026
An Independent Safety Evaluation of Kimi K2.5

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse and disinformation, and recommends mandatory safety testing for future open-weight models.

Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment

This paper systematically characterises the sensitivity of emergent misalignment (EM) in LLMs to various training choices, finding that the choice of optimiser has the largest effect on misalignment rate.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIEmpiricalRecentJun 30, 2026

Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment

Jason R. Brown, Patrick Leask, Lev McKinney

This paper systematically characterises the sensitivity of emergent misalignment (EM) in LLMs to various training choices, finding that the choice of optimiser has the largest effect on misalignment r…

View →
cs.CRcs.AIcs.CLRecent
Apr 3, 2026

An Independent Safety Evaluation of Kimi K2.5

Zheng-Xin Yong, Parv Mahajan, Andy Wang, Ida Caspary +11 more

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

View →