The adoption rate of AI tools has skyrocketed in the programming world, enabling coders to generate vast amounts of code with simple text prompts.<\/p>\n
Earlier this year, Google found<\/a> that 90 percent of software developers across the industry are using AI tools on the job, up from a mere 14 percent last year.<\/p>\n But all that convenience has come with some glaring drawbacks. The tools have repeatedly been found to be unreliable and inaccurate<\/a>, which can lead to mistakes falling through the cracks and even forcing some programmers to put in long hours to identify and correct them.<\/p>\n Adding to the reality check, a new report<\/a> by AI software company CodeRabbit found that code generated by an AI was far more error-prone than the human-written stuff \u2014 and by a significant margin. Across the 470 pull requests the company analyzed, AI code produced an average 10.83 issues per request, while human-authored code produced just 6.45.<\/p>\n In other words, AI code produced 1.7 times more issues than human code, once again highlighting major weaknesses plaguing generative AI tools.<\/p>\n \u201cThe results?\u201d CodeRabbit concluded in its report. \u201cClear, measurable, and consistent with what many developers have been feeling intuitively: AI accelerates output, but it also amplifies certain categories of mistakes.\u201d<\/p>\n Worse yet, the company found that AI-generated code produced a higher rate of \u201ccritical\u201d and \u201cmajor\u201d issues, in a \u201cmeaningful rise in substantive concerns that demand reviewer attention.\u201d<\/p>\n AI code was also most likely to contain errors related to logic and correctness. However, the biggest weakness CodeRabbit found was in code quality and readability, which are issues that can \u201cslow teams down and compound into long-term technical debt.\u201d<\/p>\n Then there are serious cybersecurity concerns, with generated code introducing issues related to improper password handling that could lead to protected information being exposed, among other insecure practices.<\/p>\n On the upside, CodeRabbit found that AI code was adept at keeping spelling errors at a minimum. Humans were twice as likely to introduce misspellings.<\/p>\n It\u2019s far from the first time we\u2019ve heard of flaws plaguing AI-generated code. In a September report<\/a>, management consultants Bain & Company concluded that despite being \u201cone of the first areas to deploy generative AI,\u201d the \u201csavings have been unremarkable\u201d in programming and \u201cresults that haven\u2019t lived up to the hype.\u201d<\/p>\n Security firm Apiiro also found<\/a> in its research that developers who used AI produce ten times more security problems than their counterparts who don\u2019t use the tech.<\/p>\n As a result, programmers are forced to pick over the generated code to ensure no glaring issues fall through the cracks. According to a\u00a0July study<\/a>\u00a0from the nonprofit Model Evaluation and Threat Research, programmers were actively being slowed down<\/a> by AI assistance tools compared to when they made do without them.<\/p>\n In short, while companies made sky-high promises about the tech making programmers\u2019 lives much easier, reality looks far more nuanced. CodeRabbit\u2019s report suggests a shift in the kinds of tasks human developers could soon be required to do \u2014 like solving issues being introduced by error-prone AI coding tools.<\/p>\n \u201cThese findings reinforce what many engineering teams have sensed throughout 2025,\u201d said CodeRabbit AI Director David Loker in a statement<\/a>. \u201cAI coding tools dramatically increase output, but they also introduce predictable, measurable weaknesses that organizations must actively mitigate.\u201d<\/p>\n