Can you look at experimental results along the way or not?
Suppose you’re running an A/B test to determine whether a web page produces more sales with one graphic versus another. You plan to randomly assign image A or B to 1,000 visitors to the page, but after only randomizing 500 visitors you want to look at the data. Is this
Read moreAn open-source development paradigm
Temporal is an open-source project focused on durable execution and workflow orchestration. Cofounder and CTO Maxim Fateev tells Ben and Ryan about the challenges of building a cloud service based on an open-source project and how Temporal is helping teams simplify their code and build more features more quickly.
Read moreOne-liner to troubleshoot LaTeX references
In LaTeX, sections are labeled with commands like label{foo} and referenced like ref{foo}. Referring to sections by labels rather than hard-coded numbers allows references to automatically update when sections are inserted, deleted, or rearranged. For every reference there ought to be a label. A label without a corresponding reference is
Read moreRetrieval-augmented Generation: Revolution or Overpromise?
Learn what RAG promises and its practical reality as we explore how RAG works, its potential benefits, its challenges and solutions. Continue reading Retrieval-augmented Generation: Revolution or Overpromise? on SitePoint.
Read moreGetting ready for a pre-hire assessment: 6 tips
If you have a pre-hire assessment coming up, it’s natural to feel a little nervous. There may be a lot at stake for you! That’s why we made this checklist for you to review before you sit down to take the assessment. Knowing you’ve got these items covered will help
Read moreWould you board a plane safety-tested by GenAI?
Ben and Ryan are joined by Robin Gupta for a conversation about benchmarking and testing AI systems. They talk through the lack of trust and confidence in AI, the inherent challenges of nondeterministic systems, the role of human verification, and whether we can (or should) expect an AI to be
Read moreWhat we learned when we gave developers access to an AI-powered tutor
The best learning happens one-on-one—that’s what decades of educational research shows, time and again. Benjamin Bloom, in his influential 1984 study, found that students who learned via 1:1 tutoring had significantly better educational performance—a difference of two standard deviations—than those who learned via traditional, one-to-many classroom instruction. To hone in
Read moreYou should keep a developer’s journal
A developer’s journal is a place to define the problem you’re solving and record what you tried and what worked.
Read moreA “well-known” series
I was reading an article [1] that refers to “a well-known trigonometric series” that I’d never seen before. This paper cites [2] which gives the series as Note that the right hand side is not a series in φ but rather in sin φ. Motivation Why might you know sin
Read moreHow to train your dream machine
Ben and Ryan talk with Vikram Chatterji, founder and CEO of Galileo, a company focused on building and evaluating generative AI apps. They discuss the challenges of benchmarking and evaluating GenAI models, the importance of data quality in AI systems, and the trade-offs between using pre-trained models and fine-tuning models
Read more