Recognizing there is no single "best" LLM, AlphaSense built a system to test and deploy various models for different tasks. This allows them to optimize for performance and even stylistic preferences, using different models for their buy-side finance clients versus their corporate users.

To get scientists to adopt AI tools, simply open-sourcing a model is not enough. A real product must provide a full-stack solution, including managed infrastructure to run expensive models, optimized workflows, and a UI. This abstracts away the complexity of MLOps, allowing scientists to focus on research.

High productivity isn't about using AI for everything. It's a disciplined workflow: breaking a task into sub-problems, using an LLM for high-leverage parts like scaffolding and tests, and reserving human focus for the core implementation. This avoids the sunk cost of forcing AI on unsuitable tasks.

An unexpected benefit of building a robust, end-to-end "Model Factory" is its suitability for AI agents. These agents are now taking over tasks within the factory, such as writing code, launching jobs, and evaluating results, creating a recursive self-improvement loop for the research process itself.

AI Engineering leverages pre-trained foundation models as a service for rapid integration. This contrasts with traditional Machine Learning Engineering, which involves building a model from scratch, from data collection to deployment, resulting in a much slower time-to-market.

Poolside rejected the standard practice of packaging and copying datasets to training clusters. Instead, they stream data just-in-time. This allows training to start immediately, even while data is still materializing, and makes experimenting with data mixes a simple configuration change, dramatically accelerating the research cycle.

Periodic Labs doesn't use a single monolithic model. Instead, a powerful language model acts as a central coordinator or "copilot." It directs experiments by calling upon smaller, highly specialized, and more efficient neural nets (e.g., those with symmetry awareness for atomic systems) as tools.

Mature AI applications are not static calls to a single large model. They are complex systems of many models that require a continuous "AI loop": tracing performance, identifying areas for improvement (cost, speed, accuracy), and constantly iterating by swapping models, fine-tuning, or refining prompts.

Despite its perceived complexity, the core work of building foundation models boils down to two things. Researchers are either improving the data going into the model or finding breakthroughs (in architecture, inference, etc.) that improve compute efficiency. This is a powerful, simplifying framework for a complex field.