{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/evaluating-frontier-models-for-dangerous","title":"Evaluating Frontier Models for Dangerous Capabilities","arxiv_id":"2403.13793","date":"2024-03-20","proceeding":null,"authors":["Mary Phuong","Matthew Aitchison","Elliot Catt","Sarah Cogan","Alexandre Kaskasoli","Victoria Krakovna","David Lindner","Matthew Rahtz","Yannis Assael","Sarah Hodkinson","Heidi Howard","Tom Lieberum","Ramana Kumar","Maria Abi Raad","Albert Webson","Lewis Ho","Sharon Lin","Sebastian Farquhar","Marcus Hutter","Gregoire Deletang","Anian Ruoss","Seliem El-Sayed","Sasha Brown","Anca Dragan","Rohin Shah","Allan Dafoe","Toby Shevlane"],"abstract":"To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new \"dangerous capability\" evaluations and pilot them on Gemini 1.0 models. Our evaluations cover four areas: (1) persuasion and deception; (2) cyber-security; (3) self-proliferation; and (4) self-reasoning. We do not find evidence of strong dangerous capabilities in the models we evaluated, but we flag early warning signs. Our goal is to help advance a rigorous science of dangerous capability evaluation, in preparation for future models.","url_abs":"https://arxiv.org/abs/2403.13793v2","url_pdf":"https://arxiv.org/pdf/2403.13793v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"evaluating-frontier-models-for-dangerous","repo_url":"https://github.com/google-deepmind/dangerous-capability-evaluations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.13793","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}