DevToolsDigest: Issue #370
This week's digest includes news and resources from RedMonk, Latent Space, and more.
Subscribe to the DevToolsDigest
All you need is 3 minutes a week to stay ahead of the devtools space. Get the most relevant industry updates, insightful discussions, and top-notch resources delivered straight to your inbox.
The Week in DevTools
How to Kill the Code Review
Humans already couldn’t keep up with code review when humans wrote code at human speed. We tell ourselves it is a quality gate, but teams have shipped without line-by-line review for decades.
Choosing the Right Small Language Model is Hard
Choosing the right model is hard. Keeping it accurate in production is even harder. Introducing Adaptive Inference; a practical framework for continuously evaluating, improving, and fine-tuning models as real-world data evolves.
What AI Coding Costs You
Which is higher risk, using AI too much, or using AI too little? Almost every developer we know uses AI for coding now. The productivity gains are real, but there are costs that don’t show up on any dashboard.
Industry Research
The Context Window Has a Physics
There’s a moment in every complex system where the intuitions you built up early become actively wrong. You hit a regime where the rules change and you don’t notice because it still appears to work. We're in that moment with context windows.
Your AI Productivity Data is Lying to You
Most engineering leaders ask: “Is AI making us faster?” That question is close to unanswerable right now. The studies are compromised, the metrics are noisy, and the developers who would report no benefit have already left the control group.
The Generative AI Policy Landscape in Open Source
How many projects have formal policies? Are most communities permissive, restrictive, or still figuring things out? What concerns are driving these decisions? Are they primarily about code quality, copyright liability, or something else entirely?