Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI)
"可扩展监督" 相关文章
Research Areas in Learning Theory (The Alignment Project by UK AISI)
Research Areas in Computational Complexity Theory (The Alignment Project by UK AISI)
Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI)
Research Areas in Cognitive Science (The Alignment Project by UK AISI)
Rational Animations' video about scalable oversight and sandwiching
Prover-Estimator Debate: A New Scalable Oversight Protocol
MIT新研究量化AI监督挑战：控制比我们聪明的AI，成功率可能不足52%？
UK AISI’s Alignment Team: Research Agenda
AGI失控率＞90%！MIT教授算出「康普顿常数」，AI地球「夺权率」已锁定？
Is weak-to-strong generalization an alignment technique?
Balancing Label Quantity and Quality for Scalable Elicitation
How should we make trade-offs between the quantity and quality of labels used for eliciting knowledge from capable AI systems?
On scalable oversight with weak LLMs judging strong LLMs
Oversharing Details of NYU’s Work on Implementing Debate as an Alignment Technique
Scalable oversight as a quantitative rather than qualitative problem
用AI监督AI，OpenAI做到了用左脚踩右脚上天
GPT-4批评GPT-4实现「自我提升」，OpenAI前超级对齐团队又一力作被公开
