OpenAI’s Realtime API redefines live interactions | Crawling websites for LLMs made easy | Tips on generating structured JSON with LLMs | DeepSeek’s Janus challenges DALL-E
Model Distillation - how to get a fast, strong and cost efficient LLM | Evaluating LLMs before upgrading | How to: Realtime audio transcriptions | New ChatGPT feature: Canvas - a better way of collaboration with LLMs
Microsoft wants to restart nuclear power plant for their AI data centers | Tips on how to make LLM outputs more consistent | How to use AI directly with Google BigQuery | OpenAI releases new "thinking" LLM
Elon Musk purchases 100.000 H100 GPUs | Increasing LLM output quality with simple prompt tricks | Saving up to 80% on LLM costs using LLM routing | The best document-data extraction solution so far
Privacy-friendly ChatGPT alternative: Open WebUI | Saving up to 90% on costs using Anthropics prompt caching | Using GPT-4o to analyze images
Free fine-tuning of GPT-4o-mini | Reflection loops: A simple & powerful way of increasing LLM output quality | Germany releases the best image LLM so far
Llama 3.1 8B: the first outstanding local-first LLM | Tutorial: How to create knowledge graphs | CopilotKit - add copilots to your app with just one line of code
Chat interface for your database | LLMs for research & writing | New tool to optimize prompts
Use-Cases and Tips & Tricks from Data and AI
