Dev
11 articles
Anthropic’s rough week: leaked models, exposed source code, and a botched GitHub takedown
Anthropic’s had a rough streak of luck lately. Last week, Fortune reported on an accidental leak of the AI company’s development of The post Anthropic’s rough week: leaked models, exposed source code, and a botched GitHub takedown appeared first on The New Stack.
Microsoft execs warn agentic AI is hollowing out the junior developer pipeline
Two of Microsoft’s most prominent developers have some words for organizations overly celebrating agentic AI’s productivity gains: You are hollowing The post Microsoft execs warn agentic AI is hollowing out the junior developer pipeline appeared first on The New Stack.
Why pgEdge thinks MCP (not an API) is the right way for AI agents to talk to databases
The Postgres open-source object-relational database system can trace its history back to some three decades, but it’s no artifact. Its The post Why pgEdge thinks MCP (not an API) is the right way for AI agents to talk to databases appeared first on The New Stack.
The TeamPCP attacks are a warning: Your CI/CD pipeline is the new front line
We built the modern software supply chain on a flawed assumption: that the systems and dependencies we rely on are The post The TeamPCP attacks are a warning: Your CI/CD pipeline is the new front line appeared first on The New Stack.
Why coding agents will break your CI/CD pipeline (and how to fix it)
Every engineering leader I speak with lately is quietly asking the exact same question. The conversation has shifted entirely. We The post Why coding agents will break your CI/CD pipeline (and how to fix it) appeared first on The New Stack.
Why Broadcom gave Velero to the CNCF Sandbox — and what it means for Kubernetes data protection
Broadcom has deep roots as one of the leading contributors to CNCF open source as it continues to extend its The post Why Broadcom gave Velero to the CNCF Sandbox — and what it means for Kubernetes data protection appeared first on The New Stack.
OpenClaw vs. Hermes Agent: The race to build AI assistants that never forget
Every developer who has used an AI coding assistant has experienced the same frustration: You spend an afternoon teaching Claude The post OpenClaw vs. Hermes Agent: The race to build AI assistants that never forget appeared first on The New Stack.
There’s a hidden tax on every AI-generated merge request
AI coding tools haven’t removed bottlenecks. They’ve moved them to the review queue, putting more pressure on senior engineers. This The post There’s a hidden tax on every AI-generated merge request appeared first on The New Stack.
Moving beyond the “magic scaling sauce” myth
The following is an excerpt from the just-published second edition of Designing Data-Intensive Applications, by Martin Kleppmann and Chris Riccomini. The post Moving beyond the “magic scaling sauce” myth appeared first on The New Stack.
Why programming became the proving ground for AI
I’ve always felt that AI found its footing in software engineering first because, frankly, the environment is honest. When you’re The post Why programming became the proving ground for AI appeared first on The New Stack.
The hidden technical debt of agentic engineering
Anyone today can build an agent locally with minimal effort. With some LLM calls, a prompt, and a few tool The post The hidden technical debt of agentic engineering appeared first on The New Stack.