Learning through human feedback — Google DeepMind

We believe that Artificial Intelligence will be one of the most important and widely beneficial scientific advances ever made, helping humanity tackle some of its greatest challenges, from climate change to delivering advanced healthcare. But for AI to deliver on this promise, we know that the technology must be built in a responsible manner and that we must consider all potential challenges and risks.

Learning through human feedback — Google DeepMind Skip to main content June 12, 2017 Research Learning through human feedback Jan Leike, Miljan Martic, Shane Legg Share We believe that Artificial Intelligence will be one of the most important and widely beneficial scientific advances ever made, helping humanity tackle some of its greatest challenges, from climate change to delivering advanced healthcare. But for AI to deliver on this promise, we know that the technology must be built in a responsible manner and that we must consider all potential challenges and risks. That is why DeepMind co-f

saved by

• vain glory

related reading

• The Era of Experience Paper.pdfstorage.googleapis.com
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
• Reinforcement learning from human feedback - Wikipediaen.wikipedia.org
• [AN #70]: Agents that help humans who are still learning about their own preferences — LessWronglesswrong.com
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Just Ask for Generalization | Eric Jangevjang.com
• Reward Hacking in Reinforcement Learning | Lil'Loglilianweng.github.io
• [2309.00267] RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackarxiv.org
• Constitutional AI: Harmlessness from AI Feedbackarxiv.org
• Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
• Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io