Tag
The author scanned AI-generated code projects and found repeated patterns of exposed API keys, leading them to build NeuralScan, a tool that scans code for secrets and dangerous patterns, explaining fixes in plain English.
An observation that Meta employees who are AI-native outside work resist AI adoption at work due to lack of incentives, highlighting a cultural mismatch.
Valentina Servile argues that good software design still matters even as AI writes more code, because the audience for well-designed code now includes AI agents as well as humans.
The author red-teamed their sandbox for running untrusted AI code and found that everything held except DNS, indicating a potential vulnerability.
Claude Opus 5 demonstrates the ability to generate an entire game from scratch using only custom code, with no external assets, indicating a significant leap in AI-driven game development.
Prelint is a tool that prevents product drift in AI-written code, helping maintain code quality and consistency.
Jacquard is a programming language designed for AI-written, human-reviewed code, with built-in effect tracking, probabilistic simulation, and canonical identity to help humans trust AI-generated programs.
Godot Engine announces a ban on AI-generated 'vibe coding' contributions due to review time bottlenecks, requiring disclosure of AI assistance and barring substantial AI-written code while allowing small completions.
The tweet argues that manually reviewing all AI-generated code creates a bottleneck and links to a resource for a better approach.
The author explains why they often reject AI-generated code even when it works, citing reasons like inability to explain the approach, overly large diffs, premature abstractions, and reduced system reasoning, and argues for mandatory human review.
Ankit predicts that traditional code reviews are dead due to AI and will be obsolete by 2026, and will discuss this at an upcoming aiDotEngineer event.
The article discusses Microsoft's policy against employees using AI for code and argues that the rapidly decreasing cost and increasing speed of AI will make it difficult for human developers to compete, challenging the idea that AI won't replace developers.
A tech commentator advises junior developers to pivot into DevOps/SRE, arguing that systems knowledge is increasingly critical because AI can write code but cannot manage production systems.