Applications that enable a natural language interface between people and data will be at the forefront of LLM enterprise adoption. At Scale, we launched a chatbot to increase access to information about our firm, but we also built it ourselves to gain an understanding of the solutions space. We've just published a blog post where we explore the architecture and share conclusions from this experience. We're also making the full source code available and free to use.
it is nearly impossible to define alignment, let alone achieve it. Human beings, in all their variance, capacity, and folly, make up the entire training pipeline, and we take such comfort in the fact that we call them all by the same name. But every human is individual, and models will change as their trainers do.
Over the last few years, building an AI startup used to require “do-it-yourself AI,” which consisted of gathering training data, labeling it, architecting complex data transformations, tuning hyperparameters, and selecting the right model. It was a herculean task, similar in complexity to the workload of the Salesforce engineer above. But in the last year or two, foundation models have emerged as a time-saving shortcut that enable entrepreneurs to do more faster. These foundation models aren’t specific to particular AI use cases, but are largely general and have something to offer almost anyone. Entrepreneurs can now decouple parts of the training data and model (which comes pre-packaged in a foundation model) from the application layer, which we at Scale call a cognitive application.