Feedback loops, and Google’s home-field advantage with LLMs
When I was at Pinterest leading product for the Discovery team, we started to leverage deep learning for our recommendations. It was always the case that while deep learning enabled a step-function change in the results (as measured by user engagement), the results got dramatically better once we took that user engagement data and fed it back into the model to further tune the results. We’d go from a place of discontinuous change with each step-function upgrade of the model, to a world with a compounding feedback loop.
When I was at Pinterest leading product for the Discovery team, we started to leverage deep learning for our recommendations. It was always the case that while deep learning enabled a step-function change in the results (as measured by user engagement), the results got dramatically better once we took that user engagement data and fed it back into the model to further tune the results. We’d go from a place of discontinuous change with each step-function upgrade of the model, to a world with a compounding feedback loop. This feedback loop that enables continuous improvement has been Google’s…
related reading
- Mediumsarahtavel.medium.com
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- What Is ChatGPT Doing … and Why Does It Work?-Stephen Wolfram Writingswritings.stephenwolfram.com
- Illustrating Reinforcement Learning from Human Feedback (RLHF)huggingface.co
- Deep Dive into LLMs like ChatGPTyoutube.com
- Why Chatbots Are Not the Future of Interfaceswattenberger.com
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Natural Language Is an Unnatural Interfacevarunshenoy.substack.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Malleable software in the age of LLMsgeoffreylitt.com
- The biggest bottleneck for large language model startups is UX | by Davis Treybig | Innovation Endeavors | Mediummedium.com
- Comparing Google and ChatGPT | Hacker Newsnews.ycombinator.com