“More compute!” is a common refrain these days in discussions about enhanced LLM performance and capability. Just scan a few recent headlines to see the resources major companies are willing to pour into getting it. In a broad sense, this refers to more and better hardware used in model training.
What makes one prompt more effective than another? And how can we quantify and document those differences? That's where prompt evaluations come in. Prompt evaluations are a way for you to assess and refine the inputs (prompts) you provide to an AI model, resulting in improved performance. Whether
In the fast-evolving world of AI, the debate between agents and workflows is becoming increasingly relevant. Businesses and their coterie of developers and prompt engineers are exploring how these two approaches can enhance their projects. But what exactly are agents and workflows, and which is right for your use case?
Traditional regression models like linear regression and random forest are tried and true. We know how they work and they're easy to audit. Not always so with large language models (LLMs) like Chat GPT, Claude, or Gemini, though that certainly hasn't stopped anyone from using them,
What is chain-of-thought and why do I need it? Raise your hand if you’ve ever been personally victimized by a math class. Showing your work, writing a proof. It can be tough, right? But it’s also a great way to make sure you really understand a concept, and