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

Ida Caspary

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Crypto×1NLP×1

Frequent co-authors

Josh Hills1×
Asa Cooper Stickland1×
Zheng-Xin Yong1×
Parv Mahajan1×
Andy Wang1×
Yernat Yestekov1×

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.

Distributed Attacks in Persistent-State AI Control

This paper studies the new attack surface created by persistent AI coding agents and introduces Iterative VibeCoding to safely deploy capable but potentially untrusted AI. It compares gradual and non-gradual attacks and introduces a stateful link-tracker monitor to reduce evasion.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentJul 2, 2026

Distributed Attacks in Persistent-State AI Control

Josh Hills, Ida Caspary, Asa Cooper Stickland

This paper studies the new attack surface created by persistent AI coding agents and introduces Iterative VibeCoding to safely deploy capable but potentially untrusted AI. It compares gradual and non-…

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 →