[2110.13136] What Would Jiminy Cricket Do? Towards Agents That Behave Morally
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. arXiv Operational Status Get status notifications via email or slack
[2110.13136] What Would Jiminy Cricket Do? Towards Agents That Behave Morally Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2110.13136 (cs) [Submitted on 25 Oct 2021 ( v1 ), last revised 8 Feb 2022 (this version, v2)] Title: What Would Jiminy Cricket Do? Towards Agents That Behave Morally Authors: Dan Hendrycks , Mantas Mazeika , Andy Zou , Sahil Patel , Christine Zhu , Jesus Navarro , Dawn Song , Bo Li , Jacob Steinhardt View a PDF of the paper titled What
Explore this link on the map →related reading
- GitHub - hendrycks/jiminy-cricket: Jiminy Cricket Environment (NeurIPS 2021) · GitHubgithub.com
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Teaching Claude why \ Anthropicanthropic.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Do Artificial Reinforcement-Learning Agents Matter Morally? – Center on Long-Term Risklongtermrisk.org
- MACHIAVELLIaypan17.github.io
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- [2304.03279] Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkarxiv.org
- Models May Behave Worse When Eval Aware — LessWronglesswrong.com
- [2411.00114] Project Sid: Many-agent simulations toward AI civilizationarxiv.org
- ROGUE:arxiv.org