Replit - Productizing Large Language Models

Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples -- as little as zero -- to…

Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples -- as little as zero -- to create language wonders. LLMs can chat, write poetry, write code, and even do basic arithmetic. However, the same properties that make LLMs magical also make them challenging from an engineering perspective. At Replit we have deployed transformer-based language models of all sizes: ~100m parameter models for search and spam, 1-10B models for a code autocomplete product we call GhostWriter, and 100B+ models for features that require a higher reasoning ability. In…

saved by

• Belinda Mo
• Pranav
• Krish Shah

related reading

• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• Malleable software in the age of LLMsgeoffreylitt.com
• Here’s how I use LLMs to help me write codesimonwillison.net
• Building LLM applications for productionhuyenchip.com
• LLM Inference Performance Engineering: Best Practices | Databricks Blogdatabricks.com
• The biggest bottleneck for large language model startups is UX | by Davis Treybig | Innovation Endeavors | Mediummedium.com
• Large Language Model: world models or surface statistics?thegradient.pub
• Deep Dive into LLMs like ChatGPTyoutube.com
• Natural Language Is an Unnatural Interfacevarunshenoy.substack.com