Sarah PackowskiI accidentally bought an AI-generated bookLet’s learn from this book’s quirks and mistakes.3d ago3d ago
Sarah PackowskiHow publishers need to adapt in the era of RAGInstead of resenting that people are scraping your content, embrace them as customers.Aug 31Aug 31
Sarah PackowskiYour team needs AI ContentOpsWhen incorporating AI into content development, AI is the easy part. The challenge is getting surrounding processes and tools right.Mar 131Mar 131
Sarah PackowskiWhat many get wrong about using LLMs in content developmentI’m talking specifically about using large language models (LLMs) to create support content like product documentation.Mar 12Mar 12
Sarah PackowskiChoosing a large language model for your project is like buying running shoesThere are are some basic attributes to consider. And getting advice helps narrow the options. But in the end, you need to try them to know…Nov 22, 20231Nov 22, 20231
Sarah PackowskiThe right way to include AI-generated content in your workIt turns out the same techniques writers, scientists, and journalists have been using for ages can help here too.Nov 19, 2023Nov 19, 2023
Sarah PackowskiWhen and why would you use an LLM for text classification?Smaller, faster, cheaper models can perform text classification very effectively. So why would it make sense to haul out a large language…Nov 12, 20231Nov 12, 20231
Sarah PackowskiHave an LLM play Devil’s Advocate to improve your chance of successA large language model (LLM) can be an effective devil’s advocate: listing arguments against a proposed plan as a way to explore the plan’s…Oct 2, 2023Oct 2, 2023
Sarah PackowskiLearning from fine-tuning data setsViewing prompts in data sets used to fine-tune a large language model can help you understand the behaviour of that model.Jul 18, 20231Jul 18, 20231
Sarah PackowskiA prompt for (almost) all modelsThere’s no one best way to prompt large language models. But here’s a pattern that’s a good place to start.Jul 9, 2023Jul 9, 2023