AI hates legacy code

Explore all

With GPT-5.1, OpenAI doubles down on steering, not scaling

OpenAI's GPT-5.1 emphasizes control and adaptability over pure performance, introducing customizable tones for users and automated reasoning depth adjustments, marking a shift in AI model development.

AI Tools & Assistants

With Code Wiki, Google wants to map the mess of modern codebases

With Code Wiki, Google wants to transform codebase navigation by creating a dynamic, structured map of repositories, enhancing developer understanding through interactive documentation and relationship tracing for more efficient software development.

Wrapper’s delight: Cursor and Windsurf’s shift to home-grown AI marks a push for independence

Cursor and Windsurf are transitioning to self-developed AI models, reducing dependence on external vendors.

Paul Sawers

6 min read

14 Nov 2025

AI Tools & Assistants

AI-Native Development

Amp ditches compaction for ‘handoff’ to fix AI’s long-context drift

Amp's new "handoff" feature replaces compaction, designed to enable smoother transitions in coding conversations by packaging relevant context into new threads while navigating complex discussions.

AI Tools & Assistants

Beyond tests: What to verify in AI-generated code

As AI transforms code generation, traditional QA approaches fall short. Jennifer Sand, CEO & co-founder of Codential, explores the necessity for a new quality framework to address issues in AI-created code.

Jennifer Sand

8 min read

13 Nov 2025

AI-Native Development

Testing & QA

Prompts are the new source code: Why we need version control

We are entering a new era of software development where prompts are quietly taking over the territory once held exclusively by source code.

Context-Bench: Measuring AI models’ context engineering proficiency

Context-Bench is a new benchmark for AI models, assessing their ability to manage information and continuity skills in complex, multi-step tasks

Code, meet crowd: Amp bets on ‘social coding’ with new public profiles

Amp is embracing “social coding,” powered by public developer profiles that let users share their projects, prompts, and agent workflows with others.

Paul Sawers

5 min read

10 Nov 2025

AI Tools & Assistants

Developer Experience

Use Automated Parallel AI Agents for Massive Refactors

Leveraging advances in AI and LLMs, this article presents a refined approach to task decomposition, enabling efficient, collaborative refactoring projects that reduce engineering timelines from months to mere days.

AI-assisted engineering: Report reveals adoption and productivity gains, but quality issues persist

A new report from developer analytics firm DX reveals that while AI coding tools may enhance productivity for developers, quality concerns remain, emphasizing that high adoption rates do not guarantee improved engineering outcomes.

Paul Sawers

12 min read

7 Nov 2025

AI Tools & Assistants

AI Engineering

OpenAI adds Safeguard to GPT-OSS, letting developers set their own safety rules

OpenAI has introduced Safeguard, a new model designed to monitor and mediate the deployment of its open-weight GPT-OSS models, marking a more measured step into open distribution.

Warp joins the pricing pivot sweeping AI developer tools

Warp, the AI-powered terminal for developers, is changing how it charges users, making it the latest in a string of coding-tool companies to revise their pricing models.

Paul Sawers

6 min read

3 Nov 2025

AI Tools & Assistants

AI Coding Tools