LTM-2-Mini is our first model with a 100 million token context window. That’s 10 million lines of code, or 750 novels. Full blog: https://t.co/oFz4A9ynVZ Evals,... See more

This week, Google announced a doubling of Gemini Pro 1.5's input context window from 1 million to 2 million tokens, and OpenAI released GPT-4o, which generates tokens 2x faster and 50% cheaper than GPT-4 Turbo and natively accepts and generates multimodal tokens. I view these developments as the latest in an 18-month trend. Given the improvements w... See more

1/ 🧵So how do we overcome 4096 token limit in OpenAI GPT requests? The answer is - Chains. Here is a short summary of @LangChainAI's documentation about chain techniques that allow you to process larger documents or many documents at once. Let's dive in! 🚀