Prompt engineering, fine tuning, and LLM chaining are most commonly considered in guiding LLM behavior. In this post, we cover three more tools, from de rigueur for complex LLM applications to speculative techniques that may not be production-ready for some time.

When creating LLM applications, a lot of emphasis is on the foundation model underpinning the app. Most likely you’ll want to modify the behavior of that model; here are some techniques for achieving that behavior modification, from well-trod to exploratory.

The general nature of LLMs makes them inherently powerful but notoriously difficult to control. Operators must defend against unintended and potentially risky interactions. Our team has investigated many of the relatively nascent solutions out there for this issue; we share what we’ve learned in this post.

Treating the process of your work as important as the result will improve the quality of your results. A lot of focus gets put on building the right thing for customers, and rightfully so, but it’s important to remember that we have to first build our workbench. Whether we do that haphazardly or intentionally can have an enormous impact on the quality of our results.

The process of making an LLM app reliable is mostly trial and error, involving spot-checking by the developer, reviews by product owners, and auto-evaluation. At Hop, we feel there’s a rich set of design decisions when it comes to auto-evaluation that aren’t regularly discussed; we share those in this post.

Think back to your last telehealth visit with a doctor. Perhaps your kid had a persistently high fever, or you had worrying chest pain. Are you sure you were interacting with a human? What makes you sure?

Machine learning researchers often don’t write tests for their code. They’re not software engineers, and their code needs only to train a model or prove out an experiment. However, at Hop, we’ve found that adding certain kinds of tests can actually accelerate research and increase confidence in results through improving code quality and encouraging reuse.

It’s now possible to train complicated models while understanding very little about how they work. There’s a widespread attitude that it’s enough to know how to code up architectures in PyTorch and correct obscure bugs, and that the math is someone else’s problem. We at Hop put ML models into production, and we’re here to tell you that the math is not someone else’s problem.