David H. Lindner

Jan 23, 2025 | lesswrong.com | Seb Farquhar |David H. Lindner |Rohin Shah

Blog post by Sebastian Farquhar, David Lindner, Rohin Shah. It discusses the paper MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking by Sebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, and Rohin Shah. Our paper tries to make agents that are safer in ways that we may not be able to  evaluate through Myopic Optimization with Non-myopic Approval (MONA).

Dec 5, 2024 | arxiv.org | David H. Lindner

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Nov 15, 2024 | securityboulevard.com | David H. Lindner

The majority of security leaders reportedly don't know what caused data security incidents at their organizations over the past 12 months. To reduce the likelihood of unknown security breaches, prioritize regular staff training and tabletop exercises. This empowers employees to identify and escalate potential risks, bolstering your overall security posture and resilience against cyberattacks.

Nov 8, 2024 | securityboulevard.com | David H. Lindner

Nov 1, 2024 | securityboulevard.com | David H. Lindner

The EU recently updated its Product Liability Directive () to reflect the critical role of software in modern society. This means software vendors are now liable for defects that cause harm, including personal injury, property damage or data loss. This change emphasizes the growing importance of prioritizing safety and security in software development.