article thumbnail

AI-native software engineering may be closer than developers think

CIO

Developers unimpressed by the early returns of generative AI for coding take note: Software development is headed toward a new era, when most code will be written by AI agents and reviewed by experienced developers, Gartner predicts. That’s what we call an AI software engineering agent.

article thumbnail

AI and Vibe Coding Are Radically Impacting Senior Devs in Code Review

The New Stack

AI agents, vibe coding , AI code review , and other AI-centric topics are all I see developers talk about on social platforms these days. Experts predict that 90% of code will be AI-generated within the next year. We now have numerous AI tools available that automate code review workflows.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

Agentic AI design: An architectural case study

CIO

Let’s review a case study and see how we can start to realize benefits now. Agentic AI design: A case study When you start doing agentic AI design you need to break down the tasks, identify the roles and map those to specific functionality that an agent will perform. The only cost is the creation of the Python code.

article thumbnail

TechCrunch+ roundup: Deep due diligence, early Q1 2023 VC results, flight lessons for angels

TechCrunch

Full TechCrunch+ articles are only available to members Use discount code TCPLUSROUNDUP to save 20% off a one- or two-year subscription Business schools teach the basics, but Mysty Rusk, who’s reviewed around 4,500 deals over the last 20 years, says the most important lessons she learned were the result of mistakes she made along the way.

article thumbnail

Collaborative Coding and Generative AI: The Future of Code Pairing

The New Stack

As per Stack Overflow’s 2024 pulse survey , 76% of lifetime developers now have or plan to have an AI code assistant available to them. From Human Pairs to Human-AI Teams Traditional pair programming involves inserting a second engineer to review each keystroke, share domain knowledge, and catch minor errors early.

article thumbnail

Case in point: taking stock of the CrowdStrike outages

CIO

Last summer, a faulty CrowdStrike software update took down millions of computers, caused billions in damages, and underscored that companies are still not able to manage third-party risks, or respond quickly and efficiently to disruptions. It was an interesting case study of global cyber impact, says Charles Clancy, CTO at Mitre.

article thumbnail

MCP Vulnerability Exposes the AI Untrusted Code Crisis

The New Stack

A critical vulnerability in Anthropic’s widely used MCP Inspector tool allows attackers to execute arbitrary code on developer machines simply by tricking them into visiting a malicious website. This isn’t about stopping the use of AI coding agents or sacrificing the massive productivity gains they provide.