The reviewed record of science sign in
Pith

arxiv: 2410.19749 · v1 · pith:WIJSCX34 · submitted 2024-10-10 · cs.CY · cs.AI

Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WIJSCX34record.jsonopen to challenge →

classification cs.CY cs.AI
keywords alignmentpotentialartificialgamingintelligencepitfallsregulatoryresearch
0
0 comments X
read the original abstract

This paper leverages insights from Alignment Theory (AT) research, which primarily focuses on the potential pitfalls of technical alignment in Artificial Intelligence, to critically examine the European Union's Artificial Intelligence Act (EU AI Act). In the context of AT research, several key failure modes - such as proxy gaming, goal drift, reward hacking or specification gaming - have been identified. These can arise when AI systems are not properly aligned with their intended objectives. The central logic of this report is: what can we learn if we treat regulatory efforts in the same way as we treat advanced AI systems? As we systematically apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.