You don’t need hosted LLMs, do you?
A comparison of self-hosted LLMs and OpenAI: cost, text generation quality, development speed, and privacy.Image generated by Stable DiffusionDuring the LLM hype, you can find a lot of articles like “Fine-tune your Private LLaMA/Falcon/Another Popular LLM”, “Train Your Own Private ChatGPT”, “How to Create a Local LLM” and others.At the same time,
Read moreThe Art of LangSmithing
A guide to testing, evaluating, and monitoring LLM calls for production using LangSmith.Continue reading on Better Programming »
Read moreWhy ORMs Are Not Always the Way To Go
Photo by Alain Bouchard on UnsplashFor many, using an Object Relational Mapper (ORM), like hibernate in Java, has become almost automatic. While ORMs are incredibly powerful and useful tools, their use should be carefully considered in certain contexts. In this article, we will look at the advantages and disadvantages of ORMs
Read moreOrthogonal Thinking in Frontend Engineering
Exploring out-of-the-box ideas to enhance software development productivityContinue reading on Better Programming »
Read morePrint, Paint, and Program a Guardian to Track Humans and Dogs Using a Pi, Camera, and Servo
A Guardian that Tracks Pets using a Pi, Camera, and ServoIn the run-up to the new Zelda release, I realized you can build a stationary guardian robot with a servo and a camera. Adding a bit of machine learning, you can then make the guardian detect objects or people or pets
Read moreThe Overflow #190: Long live the new search!
Welcome to ISSUE #190 of The Overflow! This newsletter is by developers, for developers, written and curated by the Stack Overflow team and Cassidy Williams. This week: hear from the Stackers building our AI features, consider whether LLMs suffer from an overestimation of their abilities, and test whether you can have
Read moreTest My Code, Not My Limits
Photo by John Schnobrich on UnsplashWriting testable code might seem like a task done for the sake of easier testing, but it goes beyond that. Sure, testable code does make the testing process smoother, but the benefits don’t stop there.Testable code enforces good programming practices, such as low coupling, high cohesion, and
Read moreWhy everyone should be an AppSec specialist (Ep. 598)
Laura Bell Main, founder and CEO of SafeStack, tells us why everyone should be an AppSec specialist and what she’s doing to make that happen. She and Ryan discuss why developers don’t tend to think in terms of application security, how kids bypassing security controls underscore the importance of shifting
Read more