Ai Generated Code Will Developers Still Be Needed In the past week, i had the opportunity to work with seasoned developers on real world software design. this was across multiple projects, spanning multiple countries. These developers are shipping code much faster — but the code is not proportionally better. they’re accepting ai output that roughly works, passing it through a quick mental scan, and merging it.
What Developers Say About Ai Generated Code Start small with pilot projects before scaling across the organization. ai should assist human developers, not replace them. have developers work alongside ai systems to validate generated code, provide additional context and requirements, and handle complex logic that may be beyond ai abilities. Ai can generate code, but it can’t replace problem solving, creativity, and context awareness. developers bring domain expertise, ethical reasoning, and long term planning. It may come as no surprise that a huge percentage of developers don’t trust ai generated code, but many also say it’s becoming more difficult to check for errors created by coding. In a post on x, cherny said 100% of his code is now written by anthropic’s claude code and opus 4.5. across the rest of the company, he says “pretty much 100%” of code is also ai generated.
Understanding The Risks Benefits Of Ai Code It may come as no surprise that a huge percentage of developers don’t trust ai generated code, but many also say it’s becoming more difficult to check for errors created by coding. In a post on x, cherny said 100% of his code is now written by anthropic’s claude code and opus 4.5. across the rest of the company, he says “pretty much 100%” of code is also ai generated. How does ai code generation impact developers’ roles? it shifts developers’ focus from writing repetitive code to strategizing, designing, and overseeing complex system architectures. Sixty nine percent of respondents said that less than 25% of the code they produce is ai generated. when asked about what type of code they generate with ai, 80% cited helper functions, 57% frontend components, 51% creating documentation and comments and 50% cited tests. Veracode tested 150 ai models and found 45% of generated code introduces owasp top 10 vulnerabilities. the failure rate for cross site scripting defences is 86% — and it isn't improving with newer models. here's what that looks like inside a real codebase, what you can check yourself in 30 minutes, and what the uk's national cyber security centre is now saying about it. To find out, ars reached out to several professional developers on bluesky to ask how they feel about these tools in practice, and the responses revealed a workforce that largely agrees the.
Comments are closed.