Feedback loops, and Google’s home-field advantage with LLMs | by Sarah Tavel | Feb, 2023 | Medium

When I was at Pinterest leading product for the Discovery team, we started to leverage deep learning for our recommendations. It was always…

Feedback loops, and Google’s home-field advantage with LLMs Sarah Tavel 3 min read · Feb 11, 2023 -- 2 Listen Share 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

related reading

• Feedback loops, and Google’s home-field advantage with LLMssarahtavel.com
• RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
• Google "We Have No Moat, And Neither Does OpenAI"semianalysis.com
• Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• Why Chatbots Are Not the Future of Interfaceswattenberger.com
• Delip Rao e/σ on X: "Despite the amazing results I’ve experienced with ChatGPT, this is not a correct way to look at LLM vs. Google search. Since several other tweets have made this equivalence and have been eager to spell doom for Google, twitter.com
• A simple technical explanation of RLH(AI)F | Kairos.fmkairos.fm
• Comparing Google and ChatGPT | Hacker Newsnews.ycombinator.com
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• Natural Language Is an Unnatural Interfacevarunshenoy.substack.com