Google presents Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF arxiv.org/abs/2405.19320

No LLM is secure! A year ago, we unveiled the first of many automated jailbreak capable of cracking all major LLMs. 🚨 But there is hope?! We introduce Short Circuiting: the first alignment technique that is adversarially robust. 🧵 📄 Paper: arxiv.org/abs/2406.04313

🚨Ultimate Jailbreaking Championship 2024 🚨 Hackers vs. AI in the arena. Let the battle begin! 🏆 $40,000 in Bounties 🗓️ Sept 7, 2024 @ 10AM PDT 🔗Register Now: app.grayswan.ai/arena

🚨 🔥 Multi-step reasoning is key to solving complex problems — and Transformers with Chain-of-Thought can do it surprisingly well. 🤔 But how does CoT function as a learned scratchpad that lets even shallow Transformers run sequential algorithms that would otherwise require

Excited to share our recent work! We provide a mechanistic understanding of long CoT reasoning in state-tracking: when do transformers length-generalize strongly, when they stall, and how recursive self-training pushes the boundary. 🧵(1/8)