RLF (Reinforcement Learning from Human Feedback)
A training technique where human annotators rate or compare AI-generated outputs (e.g., 'good response' vs. 'bad response'), and the AI system learns from these human signals to improve its outputs; this was a critical innovation that enabled ChatGPT to outperform earlier models.
As defined in Eric Schmidt and Craig Mundie with David Rubenstein: Genesis
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “RLF (Reinforcement Learning from Human Feedback)” →
- Google had done significant research in language models but did not achieve public recognition equivalent to OpenAI's ChatGPT because Google lacked the key innovation of reinforcement learning from human feedback (RLHF), which ChatGPT pioneered.Eric Schmidt and Craig Mundie with David Rubenstein: Genesis
- RLF (Reinforcement Learning from Human Feedback) was the critical innovation that allowed ChatGPT to outperform Google's prior AI research; RLF involved humans rating responses (good paragraph vs. bad paragraph), and this human signal during training was the final breakthrough needed for the current generation of AI systems.Eric Schmidt and Craig Mundie with David Rubenstein: Genesis