S
Zodix
Study
Academic Library
Search
Shelves
Open access
Sign in
Search or jump to…
⌘K
Mantas Mazeika · Study
Home
/
Author
Mantas Mazeika
5 works
· latest 2025
· 1 institutions
cluster: provisional
Follow
Claim this profile
h-index
5
i10
5
Citations
245
Works here
5
22
23
25
Most cited in this library
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
2023 · 105 citations
An Overview of Catastrophic AI Risks
2023 · 79 citations
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
2025 · 26 citations
X-Risk Analysis for AI Research
2022 · 19 citations
International AI Safety Report
2025 · 16 citations
Works
5 shown
International AI Safety Report
arXiv (Cornell University)
·
2025
·
92 authors
·
preprint
·
Open access
16
citations
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
neural information processing systems
·
2025
·
7 authors
·
other
·
Open access
26
citations
An Overview of Catastrophic AI Risks
arXiv (Cornell University)
·
2023
·
3 authors
·
preprint
·
Open access
79
citations
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
neural information processing systems
·
2023
·
19 authors
·
other
·
Open access
105
citations
X-Risk Analysis for AI Research
arXiv (Cornell University)
·
2022
·
2 authors
·
preprint
·
Open access
19
citations