🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Deadline! Fri Dec 9, apps DUE for 2 yr postdoc w/ me, @tarleton, Nancy Baym is not here, & danah boyd. We are looking for researchers (typically ABD or 1ish year out from their PhD) studying the intersections of tech & society—how we work, play, create, & govern. See socialmediacollective.org/2022/11/09/smc…

🚨PAPER'S OUT! 🚨Very excited that today we’re releasing a new holistic framework for evaluating the safety of generative AI systems. Big evaluation gaps remain + we suggest steps to close these. Paper: arxiv.org/abs/2310.11986, blog: bit.ly/socialethicalG… (1/n)

📢 New paper out! Super proud to share this great interdisciplinary effort (50+ amazing colleagues ❤️), where we investigate the ethical and societal implications of advanced AI assistants⭐️ 📜Looking for key insights? We have a blog post! deepmind.google/discover/blog/…

🔮 New Google DeepMind paper exploring what persuasion and manipulation in the context of language models. 👀 Existing safeguard approaches often focus on harmful outcomes of persuasion. This research argues for a deeper examination of the process of AI persuasion itself to

📣 New report out! 🎉How do we know whether an AI is “safe”? We share learnings from developing safety evaluation of large scale systems at Google DeepMind for a broad audience. Report: arxiv.org/abs/2404.14068 Key lessons: 🪡 (1/n)

Have you been thinking about the implications of anthropomorphic AI quite a bit this week? 🤔 We explore the risks of anthropomorphic AI systems in our Ethics of Advanced AI Assistants report. Key insights in thread 💡deepmind.google/discover/blog/…

New paper out! Very excited that we’re able to share STAR: SocioTechnical Approach to Red Teaming Language Models. We've made some methodological advancements focusing on human red teaming for ethical and social harms. 🧵Check out arxiv.org/abs/2406.11757

Job post! We are hiring ML Research Scientists at AISI to help explore the technical details of safety cases for advanced AI systems. Please apply if you enjoy mapping out the arguments and open research problems behind a variety of technical safety approaches! 🧵